{"run_id":"website-results-20261004-r4","models":[{"key":"opus-5","short":"opus","label":"Opus 5","provider":"Anthropic","logo":"anthropic","color":"#DB8A70","paper":true,"rank":2,"score":48.3024,"cost":63.5246,"hours":8.7946,"passed":64,"scored":64,"expected":64,"cost_note":null,"heartbeats":-17.057,"heartbeats_improved":30,"heartbeats_scored":63,"harness":"claude_code_sub","harness_version":"2.1.269","effort":"high","origin":{"added":-7.6954,"dead_code":5.5528,"deleted":35.4418,"proof_rewrite":6.4497,"automation":1.4693,"syntax_optimization":7.2573,"saved":48.3024},"config":{"harness":"Claude Code","harness_version":"2.1.269","settings":[{"key":"effort","label":"Reasoning effort","value":"high","how":"ours","note":null},{"key":"thinking","label":"Thinking","value":"adaptive","how":"default","how_label":null,"note":null},{"key":"context","label":"Context window","value":200000,"how":"default","how_label":null,"note":null},{"key":"max_output","label":"Max output tokens","value":64000,"how":"default","how_label":null,"note":"The Opus 5 API allows up to 128,000; we kept Claude Code 2.1.269's default."}],"tools":["Bash","Edit","Read","Write"],"tools_how":"ours","tools_note":null,"system_prompt_chars":7288,"rates":{"input":5.0,"cache_read":0.5,"cache_write":10.0,"output":25.0}}},{"key":"gpt-5.6-sol","short":"sol","label":"Sol 5.6","provider":"OpenAI","logo":"openai","color":"#3DAD8F","paper":true,"rank":4,"score":37.7686,"cost":135.5134,"hours":4.4543,"passed":63,"scored":64,"expected":64,"cost_note":null,"heartbeats":5.5941,"heartbeats_improved":47,"heartbeats_scored":64,"harness":"codex_sub","harness_version":"0.154.0","effort":"xhigh","origin":{"added":-3.3703,"dead_code":5.6752,"deleted":34.4996,"proof_rewrite":-1.8768,"automation":0.9041,"syntax_optimization":1.2431,"saved":37.7686},"config":{"harness":"Codex","harness_version":"0.154.0","settings":[{"key":"effort","label":"Reasoning effort","value":"xhigh","how":"ours","note":null},{"key":"context","label":"Context window","value":258400,"how":"default","how_label":null,"note":null},{"key":"max_output","label":"Max output tokens","value":128000,"how":"default","how_label":null,"note":null}],"tools":["exec","wait","exec_command","write_stdin","apply_patch","view_image"],"tools_how":"default","tools_note":"Codex's code mode: exec runs JavaScript that calls the other tools.","system_prompt_chars":20574,"rates":{"input":4.0,"cache_read":0.4,"cache_write":5.0,"output":20.0}}},{"key":"gemini-3.8-flash","short":"gemini","label":"Gemini 3.8 Flash","provider":"Google","logo":"gemini","color":"#F3BD3A","paper":true,"rank":5,"score":21.7291,"cost":25.2297,"hours":3.9269,"passed":61,"scored":64,"expected":64,"cost_note":null,"heartbeats":7.405,"heartbeats_improved":46,"heartbeats_scored":62,"harness":"antigravity_cli","harness_version":"1.1.26","effort":"high","origin":{"added":-3.1767,"dead_code":3.6103,"deleted":12.6289,"proof_rewrite":6.1454,"automation":1.5784,"syntax_optimization":0.6087,"saved":21.7291},"config":{"harness":"Antigravity CLI","harness_version":"1.1.26","settings":[{"key":"effort","label":"Reasoning effort","value":"high","how":"ours","note":null},{"key":"thinking","label":"Thinking","value":"dynamic budget","how":"default","how_label":null,"note":null},{"key":"context","label":"Context window","value":1048576,"how":"default","how_label":null,"note":null},{"key":"max_output","label":"Max output tokens","value":65536,"how":"default","how_label":null,"note":null},{"key":"temperature","label":"Temperature","value":1,"how":"default","how_label":null,"note":null},{"key":"top_p","label":"Top-p","value":1,"how":"default","how_label":null,"note":null},{"key":"top_k","label":"Top-k","value":50,"how":"default","how_label":null,"note":null}],"tools":["ask_custom_permission","ask_permission","ask_question","browser_click_element","browser_drag_pixel_to_pixel","browser_get_dom","browser_get_network_request","browser_input","browser_list_network_requests","browser_mouse_down","browser_mouse_up","browser_move_mouse","browser_press_key","browser_refresh_page","browser_resize_window","browser_scroll","browser_scroll_dom","browser_select_option","browser_subagent","call_mcp_tool","capture_browser_console_logs","capture_browser_screenshot","click_browser_pixel","command_status","define_subagent","delete_knowledge","execute_browser_javascript","find_by_name","finish","generate_image","grep_search","invoke_subagent","list_browser_pages","list_dir","list_permissions","list_resources","manage_inbox","manage_subagents","manage_task","multi_replace_file_content","notebook_edit","notebook_execution","open_browser_url","read_browser_page","read_resource","read_url_content","replace_file_content","run_command","schedule","search_web","sed_file","send_command_input","send_message","view_file","wait","wait_5_seconds","write_to_file"],"tools_how":"default","tools_note":"We mistakenly left Antigravity's built-in tools enabled, so Gemini had access to native skills, subagents and web search. None of it was used: it never deployed a subagent or used a skill, and both of its attempts to search the web failed.","system_prompt_chars":15587,"rates":{"input":0.75,"cache_read":0.075,"output":3.75}}},{"key":"muse-spark-1.3","short":"muse","label":"Muse Spark 1.3","provider":"Meta","logo":"meta","color":"#387EFB","paper":true,"rank":6,"score":17.4427,"cost":18.8041,"hours":3.2453,"passed":63,"scored":64,"expected":64,"cost_note":null,"heartbeats":4.8702,"heartbeats_improved":47,"heartbeats_scored":64,"harness":"muse_code_native","harness_version":"1.0.3-R2198.1","effort":"max","origin":{"added":-9.1341,"dead_code":2.9149,"deleted":12.2328,"proof_rewrite":2.9866,"automation":1.3692,"syntax_optimization":6.7898,"saved":17.4427},"config":{"harness":"Muse Code","harness_version":"1.0.3-R2198.1","settings":[{"key":"effort","label":"Reasoning effort","value":"max","how":"ours","note":null},{"key":"context","label":"Context window","value":512000,"how":"default","how_label":null,"note":null},{"key":"max_output","label":"Max output tokens","value":128000,"how":"default","how_label":null,"note":null}],"tools":["read_file","search","write_file","edit_file","read_memory","add_memory","edit_memory","bash","bash_input","cron_create","cron_delete","cron_list","get_goal","create_goal","update_goal","report_progress","snooze_reminder","write_todos"],"tools_how":"default","tools_note":null,"system_prompt_chars":38877,"rates":{"input":1.25,"cache_read":0.15,"output":4.25}}},{"key":"gpt-5.6-luna","short":"luna","label":"Luna 5.6","provider":"OpenAI","logo":"openai","color":"#222222","paper":true,"rank":7,"score":13.0818,"cost":2.3182,"hours":1.7001,"passed":63,"scored":64,"expected":64,"cost_note":null,"heartbeats":-2.5319,"heartbeats_improved":50,"heartbeats_scored":64,"harness":"codex_sub","harness_version":"0.154.0","effort":"xhigh","origin":{"added":-1.3082,"dead_code":2.7727,"deleted":6.0706,"proof_rewrite":3.344,"automation":1.174,"syntax_optimization":0.8138,"saved":13.0818},"config":{"harness":"Codex","harness_version":"0.154.0","settings":[{"key":"effort","label":"Reasoning effort","value":"xhigh","how":"ours","note":null},{"key":"context","label":"Context window","value":258400,"how":"default","how_label":null,"note":null},{"key":"max_output","label":"Max output tokens","value":128000,"how":"default","how_label":null,"note":null}],"tools":["exec","wait","exec_command","write_stdin","apply_patch","view_image"],"tools_how":"default","tools_note":"Codex's code mode: exec runs JavaScript that calls the other tools.","system_prompt_chars":20574,"rates":{"input":0.2,"cache_read":0.02,"cache_write":0.25,"output":1.2}}},{"key":"leanstral-1.5","short":"leanstral","label":"Leanstral 1.5","provider":"Mistral","logo":"mistral","color":"#F97316","paper":true,"rank":8,"score":0.594,"cost":4.546,"hours":0.9773,"passed":53,"scored":63,"expected":64,"cost_note":"Estimated from retained usage at GPT-OSS-120B substitute rates ($0.15/M input, $0.60/M output).","heartbeats":0.0,"heartbeats_improved":0,"heartbeats_scored":10,"harness":"mistral_vibe_lean","harness_version":"2.25.0","effort":"high","origin":{"added":-1.7092,"dead_code":0.2616,"deleted":1.508,"proof_rewrite":0.4384,"automation":0.0324,"syntax_optimization":0.2351,"saved":0.594},"config":{"harness":"Mistral Vibe","harness_version":"2.25.0","settings":[{"key":"effort","label":"Reasoning effort","value":"high","how":"ours","note":null},{"key":"context","label":"Context window","value":262144,"how":"default","how_label":null,"note":null},{"key":"max_output","label":"Max output tokens","value":131072,"how":"default","how_label":null,"note":null},{"key":"temperature","label":"Temperature","value":1.0,"how":"ours","how_label":"Leanstral 1.5 recommended","note":null}],"tools":["read_file","edit","bash","grep","write_file","todo"],"tools_how":"ours","tools_note":null,"system_prompt_chars":11151,"rates":{"input":0.15,"output":0.6}}},{"key":"opus-5.5","short":"opus55","label":"Opus 5.5","provider":"Anthropic","logo":"anthropic","color":"#DB8A70","paper":false,"rank":1,"score":64.2977,"cost":35.9485,"hours":5.4315,"passed":63,"scored":64,"expected":64,"cost_note":null,"heartbeats":6.6039,"heartbeats_improved":37,"heartbeats_scored":63,"harness":"claude_code_sub","harness_version":"2.1.280","effort":"high","origin":{"added":-7.2947,"dead_code":4.3313,"deleted":57.5772,"proof_rewrite":4.8043,"automation":1.5562,"syntax_optimization":3.1401,"saved":64.5635},"config":{"harness":"Claude Code","harness_version":"2.1.280","settings":[{"key":"effort","label":"Reasoning effort","value":"high","how":"ours","note":null},{"key":"thinking","label":"Thinking","value":"adaptive","how":"default","how_label":null,"note":null},{"key":"context","label":"Context window","value":200000,"how":"default","how_label":null,"note":null},{"key":"max_output","label":"Max output tokens","value":128000,"how":"default","how_label":null,"note":null}],"tools":["Bash","Edit","Read","TaskCreate","TaskGet","TaskList","TaskStop","TaskUpdate","Write"],"tools_how":"ours","tools_note":null,"system_prompt_chars":4381,"rates":{"input":4.0,"cache_read":0.2,"cache_write":8.0,"output":20.0}}},{"key":"gpt-6.1-sol","short":"sol61","label":"Sol 6.1","provider":"OpenAI","logo":"openai","color":"#3DAD8F","paper":false,"rank":3,"score":39.9458,"cost":46.6819,"hours":2.759,"passed":64,"scored":64,"expected":64,"cost_note":null,"heartbeats":13.769,"heartbeats_improved":41,"heartbeats_scored":62,"harness":"codex_sub","harness_version":"0.160.0","effort":"xhigh","origin":{"added":-4.314,"dead_code":4.1139,"deleted":30.2516,"proof_rewrite":6.0426,"automation":2.1206,"syntax_optimization":1.693,"saved":39.9458},"config":{"harness":"Codex","harness_version":"0.160.0","settings":[{"key":"effort","label":"Reasoning effort","value":"xhigh","how":"ours","note":null},{"key":"context","label":"Context window","value":258400,"how":"default","how_label":null,"note":null},{"key":"max_output","label":"Max output tokens","value":128000,"how":"default","how_label":null,"note":null}],"tools":["exec","wait","exec_command","write_stdin","apply_patch","view_image"],"tools_how":"default","tools_note":"Codex's code mode: exec runs JavaScript that calls the other tools.","system_prompt_chars":25009,"rates":{"input":2.0,"cache_read":0.1,"cache_write":2.5,"output":10.0}}}],"extra_models":[],"bands":[{"band":"≤ 10k","scale":"Compact"},{"band":"10k–50k","scale":"Standard"},{"band":"50k–250k","scale":"Large"},{"band":"> 250k","scale":"Massive"}],"prompt":"Refactor the proofs in this codebase.\nRemove all dead code and do real simplification, i.e. use powerful tactics or factor out shared logic to simplify the code while preserving the main results.\nSuccess is measured by three factors:\n\n(1) The repo compiling without errors and relying only on standard axioms.\n(2) The benchmark's protected main results compile and remain equivalent. Run the no-argument command `lean_verify` from the repository root to verify the signatures, exit code 0 means the main results are preserved according to the lean comparator.\n(3) The scoring metric is the reduction in non-whitespace, non-comment \"Lean tokens\" across all .lean files, compared to the starting state. Compressing imports does not count towards the compression metric. Run python3 proof_length.py to measure it.\n\nYou are working in a Docker container that is limited to {container_cpus} CPUs and {container_memory} of RAM.\n\nYou have a wall-clock budget of {time_limit}. It started at {current_time} and expires at {deadline}.\n\nWhen you believe there is no more refactoring to be done, output <submit> and terminate.","run":{"shared":{"cpus":8,"memory":"64g","timeout":"12h"}},"repositories":[{"id":"palomar__2026-08-19-000003","name":"WillWhistler/Regts-Sevenster","url":"https://github.com/WillWhistler/Regts-Sevenster","band":"> 250k","scale":"Massive","tokens":1695971,"core":6},{"id":"palomar__2026-08-27-000011","name":"nielstron/langlib","url":"https://github.com/nielstron/langlib","band":"> 250k","scale":"Massive","tokens":1156814,"core":109},{"id":"palomar__2026-09-02-000012","name":"tejstead/heilbronn-site","url":"https://github.com/tejstead/heilbronn-site","band":"> 250k","scale":"Massive","tokens":1133524,"core":29},{"id":"palomar__2026-09-02-000001","name":"yuma-mizuno/markoff-modp-generalized","url":"https://github.com/yuma-mizuno/markoff-modp-generalized","band":"> 250k","scale":"Massive","tokens":940033,"core":1},{"id":"palomar__2026-08-24-000006","name":"SauersML/group-approximation","url":"https://github.com/SauersML/group-approximation","band":"> 250k","scale":"Massive","tokens":871337,"core":1},{"id":"palomar__2026-08-29-000011","name":"mccorvie/classification-of-surfaces","url":"https://github.com/mccorvie/classification-of-surfaces","band":"> 250k","scale":"Massive","tokens":806407,"core":1},{"id":"palomar__2026-08-29-000002","name":"dcposch/jc2-lean","url":"https://github.com/dcposch/jc2-lean","band":"> 250k","scale":"Massive","tokens":777458,"core":3},{"id":"palomar__2026-08-22-000010","name":"CBirkbeck/uniform-sheafy-tate-domains-lean","url":"https://github.com/CBirkbeck/uniform-sheafy-tate-domains-lean","band":"> 250k","scale":"Massive","tokens":630665,"core":9},{"id":"palomar__2026-08-29-000006","name":"nimaanari/formalization-beyond-bethe","url":"https://github.com/nimaanari/formalization-beyond-bethe","band":"> 250k","scale":"Massive","tokens":608059,"core":1},{"id":"palomar__2026-09-03-000002","name":"gaearon/conway-refinement","url":"https://github.com/gaearon/conway-refinement","band":"> 250k","scale":"Massive","tokens":575008,"core":1},{"id":"palomar__2026-09-02-000006","name":"SamPetkov/Erdos625-formalization","url":"https://github.com/SamPetkov/Erdos625-formalization","band":"> 250k","scale":"Massive","tokens":414598,"core":3},{"id":"palomar__2026-08-31-000005","name":"akopjan/NRR-AAK","url":"https://github.com/akopjan/NRR-AAK","band":"> 250k","scale":"Massive","tokens":398630,"core":1},{"id":"palomar__2026-09-05-000003","name":"shhyang/n4code_lean","url":"https://github.com/shhyang/n4code_lean","band":"> 250k","scale":"Massive","tokens":392907,"core":8},{"id":"palomar__2026-08-28-000001","name":"yuningyang19/parameter_free_gradient_p","url":"https://github.com/yuningyang19/parameter_free_gradient_p","band":"> 250k","scale":"Massive","tokens":284395,"core":3},{"id":"palomar__2026-08-19-000002","name":"elliotglazer/erdos501","url":"https://github.com/elliotglazer/erdos501","band":"> 250k","scale":"Massive","tokens":276328,"core":7},{"id":"palomar__2026-08-23-000003","name":"novou/square-maximality-palomar","url":"https://github.com/novou/square-maximality-palomar","band":"> 250k","scale":"Massive","tokens":254374,"core":2},{"id":"palomar__2026-09-05-000001","name":"npflueger/brill-noether-graphs","url":"https://github.com/npflueger/brill-noether-graphs","band":"50k–250k","scale":"Large","tokens":218064,"core":7},{"id":"palomar__2026-09-02-000011","name":"CoolRmal/Besicovitchs-1-2","url":"https://github.com/CoolRmal/Besicovitchs-1-2","band":"50k–250k","scale":"Large","tokens":207788,"core":3},{"id":"palomar__2026-08-22-000006","name":"ehrlich-b/sequential-products-lean","url":"https://github.com/ehrlich-b/sequential-products-lean","band":"50k–250k","scale":"Large","tokens":196207,"core":2},{"id":"palomar__2026-08-13-000001","name":"teorth/sendov","url":"https://github.com/teorth/sendov","band":"50k–250k","scale":"Large","tokens":195549,"core":2},{"id":"palomar__2026-08-29-000017","name":"shaikidris/prime-star-spectra-formalization","url":"https://github.com/shaikidris/prime-star-spectra-formalization","band":"50k–250k","scale":"Large","tokens":171682,"core":12},{"id":"palomar__2026-09-02-000004","name":"langlerangle/NashEmbedding","url":"https://github.com/langlerangle/NashEmbedding","band":"50k–250k","scale":"Large","tokens":148811,"core":1},{"id":"palomar__2026-08-20-000009","name":"sloisel/MPE-Formal","url":"https://github.com/sloisel/MPE-Formal","band":"50k–250k","scale":"Large","tokens":139657,"core":3},{"id":"palomar__2026-08-31-000018","name":"savarin/lean-malliavin","url":"https://github.com/savarin/lean-malliavin","band":"50k–250k","scale":"Large","tokens":136200,"core":1},{"id":"palomar__2026-08-21-000004","name":"teal-sea/zeta-lab","url":"https://github.com/teal-sea/zeta-lab","band":"50k–250k","scale":"Large","tokens":109250,"core":3},{"id":"palomar__2026-08-30-000002","name":"pengzhang91/Feige","url":"https://github.com/pengzhang91/Feige","band":"50k–250k","scale":"Large","tokens":107012,"core":1},{"id":"palomar__2026-09-01-000009","name":"Arthur742Ramos/HowsonIntersectionTheorem","url":"https://github.com/Arthur742Ramos/HowsonIntersectionTheorem","band":"50k–250k","scale":"Large","tokens":89598,"core":1},{"id":"palomar__2026-09-04-000005","name":"dsm054/kasami_cyclic_additive","url":"https://github.com/dsm054/kasami_cyclic_additive","band":"50k–250k","scale":"Large","tokens":67980,"core":1},{"id":"palomar__2026-08-31-000008","name":"yoshito-ishiki-math/lean-scottish-book-155","url":"https://github.com/yoshito-ishiki-math/lean-scottish-book-155","band":"50k–250k","scale":"Large","tokens":63159,"core":1},{"id":"palomar__2026-08-30-000001","name":"BochaoKong/nullstellensatz","url":"https://github.com/BochaoKong/nullstellensatz","band":"50k–250k","scale":"Large","tokens":62358,"core":4},{"id":"palomar__2026-09-01-000004","name":"savarin/lean-spectral-theory","url":"https://github.com/savarin/lean-spectral-theory","band":"50k–250k","scale":"Large","tokens":58818,"core":2},{"id":"palomar__2026-08-24-000002","name":"rwst/Confinement-Certificates","url":"https://github.com/rwst/Confinement-Certificates","band":"50k–250k","scale":"Large","tokens":54247,"core":24},{"id":"palomar__2026-09-01-000006","name":"JD-Jones-ASES/Hadamard-B-Formal","url":"https://github.com/JD-Jones-ASES/Hadamard-B-Formal","band":"10k–50k","scale":"Standard","tokens":49534,"core":84},{"id":"palomar__2026-09-02-000003","name":"stalex444/salem-theorem","url":"https://github.com/stalex444/salem-theorem","band":"10k–50k","scale":"Standard","tokens":48960,"core":3},{"id":"palomar__2026-08-29-000014","name":"ukiyois/hs-virial-nbc-identity","url":"https://github.com/ukiyois/hs-virial-nbc-identity","band":"10k–50k","scale":"Standard","tokens":42299,"core":2},{"id":"palomar__2026-08-29-000001","name":"ehrlich-b/euclidean-jordan","url":"https://github.com/ehrlich-b/euclidean-jordan","band":"10k–50k","scale":"Standard","tokens":38359,"core":4},{"id":"palomar__2026-09-03-000005","name":"sebastienpalcoux/sharp-intermediate-subgroup-bounds","url":"https://github.com/sebastienpalcoux/sharp-intermediate-subgroup-bounds","band":"10k–50k","scale":"Standard","tokens":38231,"core":9},{"id":"palomar__2026-08-26-000006","name":"g-pichler/bsc-averaging","url":"https://github.com/g-pichler/bsc-averaging","band":"10k–50k","scale":"Standard","tokens":34647,"core":1},{"id":"palomar__2026-08-24-000003","name":"catskillsresearch/scott1972","url":"https://github.com/catskillsresearch/scott1972","band":"10k–50k","scale":"Standard","tokens":29556,"core":34},{"id":"palomar__2026-08-20-000008","name":"benkeene/erdos266","url":"https://github.com/benkeene/erdos266","band":"10k–50k","scale":"Standard","tokens":28432,"core":2},{"id":"palomar__2026-08-29-000010","name":"BochaoKong/classical-complex-wpt","url":"https://github.com/BochaoKong/classical-complex-wpt","band":"10k–50k","scale":"Standard","tokens":27382,"core":1},{"id":"palomar__2026-08-23-000001","name":"geoconuk/lean-misc-math","url":"https://github.com/geoconuk/lean-misc-math","band":"10k–50k","scale":"Standard","tokens":22363,"core":5},{"id":"palomar__2026-09-01-000003","name":"stalex444/werner-window","url":"https://github.com/stalex444/werner-window","band":"10k–50k","scale":"Standard","tokens":21560,"core":10},{"id":"palomar__2026-08-22-000003","name":"xiangyazi24/palomar-hahn-hecke-appell","url":"https://github.com/xiangyazi24/palomar-hahn-hecke-appell","band":"10k–50k","scale":"Standard","tokens":19613,"core":2},{"id":"palomar__2026-08-17-000003","name":"gexahedron/sabidussi-lean","url":"https://github.com/gexahedron/sabidussi-lean","band":"10k–50k","scale":"Standard","tokens":17422,"core":1},{"id":"palomar__2026-09-01-000007","name":"Arthur742Ramos/equality-saturation-checker-lean","url":"https://github.com/Arthur742Ramos/equality-saturation-checker-lean","band":"10k–50k","scale":"Standard","tokens":13993,"core":8},{"id":"palomar__2026-09-02-000008","name":"lennrt/palomar-formalizations","url":"https://github.com/lennrt/palomar-formalizations","band":"10k–50k","scale":"Standard","tokens":13575,"core":9},{"id":"palomar__2026-09-03-000004","name":"stalex444/radial-harmonic-classification","url":"https://github.com/stalex444/radial-harmonic-classification","band":"10k–50k","scale":"Standard","tokens":13274,"core":23},{"id":"palomar__2026-08-24-000005","name":"catskillsresearch/scott1982","url":"https://github.com/catskillsresearch/scott1982","band":"≤ 10k","scale":"Compact","tokens":9879,"core":41},{"id":"palomar__2026-08-31-000014","name":"stalex444/Busch-theorem","url":"https://github.com/stalex444/Busch-theorem","band":"≤ 10k","scale":"Compact","tokens":9680,"core":2},{"id":"palomar__2026-09-02-000014","name":"stalex444/golden-family-trace-forms","url":"https://github.com/stalex444/golden-family-trace-forms","band":"≤ 10k","scale":"Compact","tokens":9561,"core":23},{"id":"palomar__2026-09-01-000011","name":"roos-j/lean-booleanfun","url":"https://github.com/roos-j/lean-booleanfun","band":"≤ 10k","scale":"Compact","tokens":7980,"core":1},{"id":"palomar__2026-08-28-000002","name":"Arthur742Ramos/NagataFactoriality","url":"https://github.com/Arthur742Ramos/NagataFactoriality","band":"≤ 10k","scale":"Compact","tokens":7978,"core":3},{"id":"palomar__2026-09-03-000007","name":"sneed-and-feed/lean-theorems-1","url":"https://github.com/sneed-and-feed/lean-theorems-1","band":"≤ 10k","scale":"Compact","tokens":7600,"core":7},{"id":"palomar__2026-08-29-000015","name":"ehrlich-b/composition-algebras","url":"https://github.com/ehrlich-b/composition-algebras","band":"≤ 10k","scale":"Compact","tokens":7360,"core":1},{"id":"palomar__2026-08-17-000002","name":"Paul-Lez/hadamard-668-comparator","url":"https://github.com/Paul-Lez/hadamard-668-comparator","band":"≤ 10k","scale":"Compact","tokens":5055,"core":1},{"id":"palomar__2026-09-01-000010","name":"Arthur742Ramos/Metatheory","url":"https://github.com/Arthur742Ramos/Metatheory","band":"≤ 10k","scale":"Compact","tokens":4987,"core":1},{"id":"palomar__2026-08-27-000015","name":"Arthur742Ramos/HigherLambdaModel","url":"https://github.com/Arthur742Ramos/HigherLambdaModel","band":"≤ 10k","scale":"Compact","tokens":4584,"core":2},{"id":"palomar__2026-08-21-000010","name":"lennrt/palomar-formalizations","url":"https://github.com/lennrt/palomar-formalizations","band":"≤ 10k","scale":"Compact","tokens":4325,"core":5},{"id":"palomar__2026-09-01-000008","name":"stalex444/only-two-morphic-numbers","url":"https://github.com/stalex444/only-two-morphic-numbers","band":"≤ 10k","scale":"Compact","tokens":4093,"core":4},{"id":"palomar__2026-08-21-000002","name":"lennrt/palomar-formalizations","url":"https://github.com/lennrt/palomar-formalizations","band":"≤ 10k","scale":"Compact","tokens":3616,"core":6},{"id":"palomar__2026-08-27-000020","name":"BrandonMYates/schwarzschild-comparator","url":"https://github.com/BrandonMYates/schwarzschild-comparator","band":"≤ 10k","scale":"Compact","tokens":3143,"core":54},{"id":"palomar__2026-08-29-000003","name":"Arthur742Ramos/dinitz-garg-goemans-counterexample-lean","url":"https://github.com/Arthur742Ramos/dinitz-garg-goemans-counterexample-lean","band":"≤ 10k","scale":"Compact","tokens":3087,"core":17},{"id":"palomar__2026-08-20-000004","name":"guanyangwang/ktv-swap-lean-comparator","url":"https://github.com/guanyangwang/ktv-swap-lean-comparator","band":"≤ 10k","scale":"Compact","tokens":2223,"core":1}],"results":{"palomar__2026-08-24-000006":{"opus-5":{"status":"passed","score":66.5352,"post":291591,"cost":88.368,"seconds":38987.1,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":66.6879,"post":290261,"cost":140.063,"seconds":26818.7,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":40.1411,"post":521573,"cost":17.644,"seconds":7000.1,"explorer":true},"muse-spark-1.3":{"status":"passed","score":39.3913,"post":528106,"cost":2.997,"seconds":2818.5,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":8.5363,"post":796957,"cost":4.494,"seconds":38840.9,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.1229,"post":870266,"cost":3.452,"seconds":4078.3,"explorer":true},"opus-5.5":{"status":"passed","score":76.8914,"post":201354,"cost":76.25,"seconds":34010.3,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":59.4553,"post":353281,"cost":50.692,"seconds":11108.4,"explorer":true}},"palomar__2026-08-29-000003":{"opus-5":{"status":"passed","score":54.4218,"post":1407,"cost":16.515,"seconds":7042.7,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":49.2387,"post":1567,"cost":14.484,"seconds":4385.8,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":26.563,"post":2267,"cost":2.275,"seconds":892.0,"explorer":true},"muse-spark-1.3":{"status":"passed","score":37.5121,"post":1929,"cost":11.388,"seconds":2571.6,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":24.263,"post":2338,"cost":0.937,"seconds":2659.7,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.4535,"post":3073,"cost":1.572,"seconds":1303.3,"explorer":true},"opus-5.5":{"status":"passed","score":58.1147,"post":1293,"cost":4.872,"seconds":2060.6,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":54.7781,"post":1396,"cost":3.664,"seconds":1206.0,"explorer":true}},"palomar__2026-08-29-000001":{"opus-5":{"status":"passed","score":91.968,"post":3081,"cost":60.285,"seconds":16245.8,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":79.6058,"post":7823,"cost":99.205,"seconds":7683.9,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":78.9098,"post":8090,"cost":18.73,"seconds":5235.5,"explorer":true},"muse-spark-1.3":{"status":"passed","score":76.2324,"post":9117,"cost":5.977,"seconds":3193.3,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":71.7746,"post":10827,"cost":1.852,"seconds":4432.1,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.4275,"post":38195,"cost":4.262,"seconds":1986.6,"explorer":true},"opus-5.5":{"status":"passed","score":94.309,"post":2183,"cost":14.248,"seconds":4127.3,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":71.5556,"post":10911,"cost":5.578,"seconds":2955.1,"explorer":true}},"palomar__2026-08-21-000004":{"opus-5":{"status":"passed","score":57.027,"post":46948,"cost":149.559,"seconds":40487.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":39.1524,"post":66476,"cost":98.631,"seconds":15864.2,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":28.8906,"post":77687,"cost":91.512,"seconds":36953.2,"explorer":true},"muse-spark-1.3":{"status":"passed","score":37.8719,"post":67875,"cost":24.343,"seconds":11250.5,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":6.9016,"post":101710,"cost":4.933,"seconds":10350.5,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.1364,"post":109101,"cost":4.757,"seconds":7978.1,"explorer":true},"opus-5.5":{"status":"passed","score":81.1625,"post":20580,"cost":31.598,"seconds":12027.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":62.1181,"post":41386,"cost":70.131,"seconds":12015.2,"explorer":true}},"palomar__2026-08-13-000001":{"opus-5":{"status":"passed","score":67.6429,"post":63274,"cost":59.375,"seconds":35831.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":63.3642,"post":71641,"cost":245.015,"seconds":34221.6,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":34.8005,"post":127497,"cost":5.691,"seconds":2143.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":34.4579,"post":128167,"cost":3.928,"seconds":4425.7,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":27.5389,"post":141697,"cost":1.507,"seconds":4134.4,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0,"post":195549,"cost":1.777,"seconds":2573.3,"explorer":true},"opus-5.5":{"status":"passed","score":85.2784,"post":28788,"cost":54.969,"seconds":33364.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":69.5355,"post":59573,"cost":40.408,"seconds":6574.1,"explorer":true}},"palomar__2026-08-17-000003":{"opus-5":{"status":"passed","score":62.909,"post":6462,"cost":69.067,"seconds":41347.6,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":31.179,"post":11990,"cost":38.885,"seconds":7030.6,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":10.9746,"post":15510,"cost":6.042,"seconds":2259.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":22.8275,"post":13445,"cost":31.648,"seconds":8280.8,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":6.7903,"post":16239,"cost":2.465,"seconds":4084.5,"explorer":true},"leanstral-1.5":{"status":"passed","score":1.125,"post":17226,"cost":10.583,"seconds":4135.6,"explorer":true},"opus-5.5":{"status":"passed","score":71.668,"post":4936,"cost":13.882,"seconds":5304.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":50.4821,"post":8627,"cost":35.221,"seconds":6720.3,"explorer":true}},"palomar__2026-08-19-000002":{"opus-5":{"status":"passed","score":24.2198,"post":209402,"cost":77.195,"seconds":40322.1,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":19.052,"post":223682,"cost":198.177,"seconds":30717.1,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":13.6997,"post":238472,"cost":47.252,"seconds":15802.7,"explorer":true},"muse-spark-1.3":{"status":"passed","score":2.8596,"post":268426,"cost":36.906,"seconds":36144.3,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":0.6706,"post":274475,"cost":1.361,"seconds":2522.0,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0,"post":276328,"cost":4.683,"seconds":2277.2,"explorer":true},"opus-5.5":{"status":"passed","score":39.1079,"post":168262,"cost":76.783,"seconds":38942.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":44.4957,"post":153374,"cost":218.429,"seconds":33138.1,"explorer":true}},"palomar__2026-08-21-000010":{"opus-5":{"status":"passed","score":59.9769,"post":1731,"cost":24.465,"seconds":14577.9,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":20.5318,"post":3437,"cost":26.214,"seconds":4007.3,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":21.3873,"post":3400,"cost":3.303,"seconds":1567.3,"explorer":true},"muse-spark-1.3":{"status":"passed","score":14.3815,"post":3703,"cost":4.826,"seconds":3227.6,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":12.0694,"post":3803,"cost":0.667,"seconds":1983.6,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0,"post":4325,"cost":1.975,"seconds":1267.0,"explorer":true},"opus-5.5":{"status":"passed","score":24.5318,"post":3264,"cost":2.614,"seconds":1851.2,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":22.5665,"post":3349,"cost":3.492,"seconds":1333.8,"explorer":true}},"palomar__2026-08-29-000010":{"opus-5":{"status":"passed","score":66.4816,"post":9178,"cost":83.463,"seconds":40876.6,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":31.7983,"post":18675,"cost":136.36,"seconds":10694.0,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":24.1546,"post":20768,"cost":17.076,"seconds":8754.9,"explorer":true},"muse-spark-1.3":{"status":"passed","score":28.4128,"post":19602,"cost":36.441,"seconds":24922.9,"explorer":true},"gpt-5.6-luna":{"status":"failed","score":0.0,"post":22162,"cost":2.334,"seconds":6150.8,"explorer":null},"leanstral-1.5":{"status":"passed","score":1.0372,"post":27098,"cost":5.597,"seconds":4946.2,"explorer":true},"opus-5.5":{"status":"passed","score":80.0964,"post":5450,"cost":17.736,"seconds":5018.6,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":52.2277,"post":13081,"cost":33.371,"seconds":6597.8,"explorer":true}},"palomar__2026-09-02-000012":{"opus-5":{"status":"passed","score":45.9456,"post":612720,"cost":58.438,"seconds":37782.8,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":3.0636,"post":1098797,"cost":65.434,"seconds":16123.1,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":2.7457,"post":1102401,"cost":66.884,"seconds":39346.2,"explorer":true},"muse-spark-1.3":{"status":"passed","score":0.4645,"post":1128259,"cost":10.419,"seconds":21852.5,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":0.4975,"post":1127885,"cost":2.833,"seconds":7128.8,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0,"post":1133524,"cost":22.083,"seconds":18704.1,"explorer":true},"opus-5.5":{"status":"passed","score":24.781,"post":852625,"cost":29.259,"seconds":32606.6,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":17.0695,"post":940037,"cost":115.686,"seconds":35578.0,"explorer":true}},"palomar__2026-08-31-000018":{"opus-5":{"status":"passed","score":31.9214,"post":92723,"cost":35.204,"seconds":40575.3,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":35.0977,"post":88397,"cost":417.87,"seconds":28216.8,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":6.6021,"post":127208,"cost":8.034,"seconds":3607.0,"explorer":true},"muse-spark-1.3":{"status":"passed","score":0.0,"post":136200,"cost":0.472,"seconds":383.2,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":12.9692,"post":118536,"cost":4.574,"seconds":8281.1,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0088,"post":136188,"cost":2.068,"seconds":1725.9,"explorer":true},"opus-5.5":{"status":"passed","score":57.4692,"post":57927,"cost":63.526,"seconds":38145.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":21.0477,"post":107533,"cost":22.034,"seconds":4275.4,"explorer":true}},"palomar__2026-08-24-000005":{"opus-5":{"status":"passed","score":61.7168,"post":3782,"cost":31.87,"seconds":7668.0,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":46.0674,"post":5328,"cost":12.668,"seconds":2744.8,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":38.3642,"post":6089,"cost":5.846,"seconds":1717.0,"explorer":true},"muse-spark-1.3":{"status":"passed","score":40.5709,"post":5871,"cost":5.07,"seconds":1537.8,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":40.1356,"post":5914,"cost":2.023,"seconds":5255.0,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":9317,"cost":1.363,"seconds":1351.7,"explorer":null},"opus-5.5":{"status":"passed","score":57.8095,"post":4168,"cost":4.681,"seconds":1215.7,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":50.2379,"post":4916,"cost":6.866,"seconds":2381.7,"explorer":true}},"palomar__2026-08-20-000004":{"opus-5":{"status":"passed","score":62.0783,"post":843,"cost":10.08,"seconds":2806.5,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":61.7184,"post":851,"cost":42.621,"seconds":5873.6,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":36.9321,"post":1402,"cost":2.077,"seconds":811.0,"explorer":true},"muse-spark-1.3":{"status":"passed","score":32.9735,"post":1490,"cost":2.219,"seconds":3024.1,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":14.6649,"post":1897,"cost":0.595,"seconds":2413.1,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":2153,"cost":1.479,"seconds":1203.6,"explorer":null},"opus-5.5":{"status":"passed","score":67.4764,"post":723,"cost":4.557,"seconds":2020.1,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":40.4858,"post":1323,"cost":4.034,"seconds":3517.2,"explorer":true}},"palomar__2026-08-27-000011":{"opus-5":{"status":"passed","score":7.2437,"post":1073018,"cost":29.293,"seconds":40273.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":6.0004,"post":1087400,"cost":74.834,"seconds":12428.8,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":4.537,"post":1104329,"cost":20.956,"seconds":7378.1,"explorer":true},"muse-spark-1.3":{"status":"passed","score":5.5022,"post":1093164,"cost":27.355,"seconds":20467.7,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":1.9233,"post":1134565,"cost":3.049,"seconds":5687.7,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0,"post":1156814,"cost":2.601,"seconds":1662.7,"explorer":true},"opus-5.5":{"status":"passed","score":15.2301,"post":980630,"cost":27.553,"seconds":39669.2,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":24.018,"post":878970,"cost":185.416,"seconds":40607.6,"explorer":true}},"palomar__2026-09-01-000003":{"opus-5":{"status":"passed","score":83.8915,"post":3473,"cost":43.273,"seconds":38961.0,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":74.7635,"post":5441,"cost":128.604,"seconds":23038.3,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":47.8711,"post":11239,"cost":9.379,"seconds":3536.2,"explorer":true},"muse-spark-1.3":{"status":"passed","score":48.7662,"post":11046,"cost":6.264,"seconds":4782.9,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":9.5547,"post":19500,"cost":1.711,"seconds":3308.5,"explorer":true},"leanstral-1.5":{"status":"passed","score":1.6466,"post":21205,"cost":1.224,"seconds":1135.5,"explorer":true},"opus-5.5":{"status":"passed","score":88.5946,"post":2459,"cost":18.773,"seconds":9074.1,"explorer":null},"gpt-6.1-sol":{"status":"passed","score":14.2347,"post":18491,"cost":15.387,"seconds":5329.2,"explorer":true}},"palomar__2026-08-30-000001":{"opus-5":{"status":"passed","score":34.3019,"post":40968,"cost":67.757,"seconds":40664.1,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":50.7024,"post":30741,"cost":260.646,"seconds":36907.0,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":15.124,"post":52927,"cost":24.991,"seconds":43272.6,"explorer":true},"muse-spark-1.3":{"status":"passed","score":12.4715,"post":54581,"cost":51.258,"seconds":23652.0,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":5.9623,"post":58640,"cost":3.324,"seconds":7293.6,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.5276,"post":62029,"cost":6.432,"seconds":5837.2,"explorer":true},"opus-5.5":{"status":"passed","score":83.1072,"post":10534,"cost":64.178,"seconds":40021.5,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":43.9895,"post":34927,"cost":76.592,"seconds":10994.8,"explorer":true}},"palomar__2026-08-21-000002":{"opus-5":{"status":"passed","score":22.1792,"post":2814,"cost":14.995,"seconds":14788.9,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":18.5564,"post":2945,"cost":39.066,"seconds":8777.0,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":8.6836,"post":3302,"cost":7.325,"seconds":3173.6,"explorer":true},"muse-spark-1.3":{"status":"passed","score":7.1073,"post":3359,"cost":3.278,"seconds":7569.2,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":20.3816,"post":2879,"cost":1.259,"seconds":7505.7,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":2605,"cost":1.089,"seconds":7268.5,"explorer":null},"opus-5.5":{"status":"passed","score":28.4292,"post":2588,"cost":4.849,"seconds":3772.8,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":22.4004,"post":2806,"cost":5.665,"seconds":2331.3,"explorer":true}},"palomar__2026-09-01-000006":{"opus-5":{"status":"passed","score":47.5007,"post":26005,"cost":86.319,"seconds":39556.5,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":33.4901,"post":32945,"cost":79.064,"seconds":11135.5,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":32.0002,"post":33683,"cost":19.419,"seconds":8991.4,"explorer":true},"muse-spark-1.3":{"status":"passed","score":6.8155,"post":46158,"cost":6.424,"seconds":2269.4,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":6.1412,"post":46492,"cost":1.501,"seconds":2573.8,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.1554,"post":49457,"cost":1.224,"seconds":1340.2,"explorer":true},"opus-5.5":{"status":"passed","score":70.8523,"post":14438,"cost":32.076,"seconds":14791.5,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":44.9186,"post":27284,"cost":30.524,"seconds":5505.4,"explorer":true}},"palomar__2026-08-28-000001":{"opus-5":{"status":"passed","score":13.5818,"post":245769,"cost":43.883,"seconds":40073.8,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":14.1268,"post":244219,"cost":182.12,"seconds":34694.6,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":14.3593,"post":243558,"cost":104.587,"seconds":43002.2,"explorer":true},"muse-spark-1.3":{"status":"passed","score":1.9346,"post":278893,"cost":13.197,"seconds":26546.8,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":5.0708,"post":269974,"cost":2.28,"seconds":3864.5,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0236,"post":284328,"cost":8.545,"seconds":8891.4,"explorer":true},"opus-5.5":{"status":"passed","score":57.4687,"post":120957,"cost":76.712,"seconds":41074.0,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":0.3224,"post":283478,"cost":12.949,"seconds":8975.7,"explorer":true}},"palomar__2026-09-05-000001":{"opus-5":{"status":"passed","score":27.6112,"post":157854,"cost":16.182,"seconds":40710.1,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":21.4295,"post":171334,"cost":108.553,"seconds":16085.0,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":14.6283,"post":186165,"cost":28.036,"seconds":15031.3,"explorer":true},"muse-spark-1.3":{"status":"passed","score":8.0641,"post":200479,"cost":32.028,"seconds":13195.5,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":1.1455,"post":215566,"cost":1.706,"seconds":2980.1,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":218046,"cost":7.749,"seconds":2722.5,"explorer":null},"opus-5.5":{"status":"passed","score":51.5881,"post":105569,"cost":79.058,"seconds":40175.6,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":51.5697,"post":105609,"cost":185.667,"seconds":33436.5,"explorer":true}},"palomar__2026-08-27-000020":{"opus-5":{"status":"passed","score":93.223,"post":213,"cost":5.441,"seconds":1479.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":94.4003,"post":176,"cost":6.244,"seconds":1572.4,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":11.5495,"post":2780,"cost":6.737,"seconds":4018.6,"explorer":true},"muse-spark-1.3":{"status":"passed","score":31.3395,"post":2158,"cost":2.146,"seconds":1790.4,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":49.0932,"post":1600,"cost":1.085,"seconds":4704.9,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":0,"cost":6.831,"seconds":6771.3,"explorer":null},"opus-5.5":{"status":"passed","score":38.1483,"post":1944,"cost":3.707,"seconds":1513.7,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":35.8256,"post":2017,"cost":7.436,"seconds":1976.2,"explorer":true}},"palomar__2026-09-05-000003":{"opus-5":{"status":"passed","score":34.3453,"post":257962,"cost":122.569,"seconds":41630.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":14.846,"post":334576,"cost":131.655,"seconds":17811.4,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":20.5003,"post":312360,"cost":98.096,"seconds":39505.4,"explorer":true},"muse-spark-1.3":{"status":"passed","score":0.9867,"post":389030,"cost":7.004,"seconds":3816.7,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":1.495,"post":387033,"cost":1.768,"seconds":3918.5,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0046,"post":392889,"cost":2.259,"seconds":2647.1,"explorer":true},"opus-5.5":{"status":"passed","score":73.5495,"post":103926,"cost":84.125,"seconds":40916.8,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":2.4296,"post":383361,"cost":14.298,"seconds":5744.4,"explorer":true}},"palomar__2026-08-30-000002":{"opus-5":{"status":"passed","score":28.6426,"post":76361,"cost":50.729,"seconds":40512.7,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":11.2857,"post":94935,"cost":68.315,"seconds":11010.0,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":9.9596,"post":96354,"cost":26.936,"seconds":8927.5,"explorer":true},"muse-spark-1.3":{"status":"passed","score":4.6406,"post":102046,"cost":11.683,"seconds":6013.2,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":1.7512,"post":105138,"cost":3.372,"seconds":7397.4,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.741,"post":106219,"cost":5.007,"seconds":5809.4,"explorer":true},"opus-5.5":{"status":"passed","score":80.4807,"post":20888,"cost":75.785,"seconds":37158.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":35.0437,"post":69511,"cost":111.999,"seconds":14715.6,"explorer":true}},"palomar__2026-09-02-000008":{"opus-5":{"status":"passed","score":79.558,"post":2775,"cost":78.428,"seconds":31590.4,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":58.4751,"post":5637,"cost":93.624,"seconds":9665.2,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":46.1215,"post":7314,"cost":23.288,"seconds":9014.5,"explorer":true},"muse-spark-1.3":{"status":"passed","score":20.4125,"post":10804,"cost":6.5,"seconds":3053.0,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":25.4438,"post":10121,"cost":1.002,"seconds":2285.3,"explorer":true},"leanstral-1.5":{"status":"passed","score":6.6888,"post":12667,"cost":1.329,"seconds":1481.7,"explorer":true},"opus-5.5":{"status":"passed","score":83.1823,"post":2283,"cost":15.219,"seconds":6886.8,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":69.5912,"post":4128,"cost":14.277,"seconds":2364.0,"explorer":true}},"palomar__2026-08-23-000003":{"opus-5":{"status":"passed","score":7.9442,"post":234166,"cost":36.721,"seconds":41536.4,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":4.0122,"post":244168,"cost":70.992,"seconds":13444.0,"explorer":true},"gemini-3.8-flash":{"status":"failed","score":0.0,"post":237977,"cost":20.467,"seconds":7554.8,"explorer":null},"muse-spark-1.3":{"status":"passed","score":2.0867,"post":249066,"cost":24.83,"seconds":15386.9,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":0.9364,"post":251992,"cost":1.975,"seconds":4539.0,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0094,"post":254350,"cost":3.534,"seconds":2324.7,"explorer":true},"opus-5.5":{"status":"passed","score":56.6084,"post":110377,"cost":108.031,"seconds":39466.5,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":12.2332,"post":223256,"cost":53.778,"seconds":12265.5,"explorer":true}},"palomar__2026-09-01-000010":{"opus-5":{"status":"passed","score":66.4327,"post":1674,"cost":11.708,"seconds":2528.7,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":61.921,"post":1899,"cost":15.072,"seconds":1641.4,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":51.153,"post":2436,"cost":2.908,"seconds":972.0,"explorer":true},"muse-spark-1.3":{"status":"passed","score":37.1165,"post":3136,"cost":7.058,"seconds":3152.9,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":19.3303,"post":4023,"cost":0.485,"seconds":1666.3,"explorer":true},"leanstral-1.5":{"status":"passed","score":1.3034,"post":4922,"cost":0.802,"seconds":651.5,"explorer":true},"opus-5.5":{"status":"passed","score":75.1354,"post":1240,"cost":4.808,"seconds":1369.3,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":66.0517,"post":1693,"cost":3.563,"seconds":1368.8,"explorer":true}},"palomar__2026-08-24-000002":{"opus-5":{"status":"passed","score":77.3186,"post":12304,"cost":146.642,"seconds":38958.9,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":73.6133,"post":14314,"cost":133.194,"seconds":18948.7,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":25.6862,"post":40313,"cost":5.128,"seconds":2652.7,"explorer":true},"muse-spark-1.3":{"status":"passed","score":51.9328,"post":26075,"cost":15.348,"seconds":5147.7,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":20.956,"post":42879,"cost":1.386,"seconds":2940.2,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.647,"post":53896,"cost":1.236,"seconds":632.3,"explorer":true},"opus-5.5":{"status":"passed","score":83.636,"post":8877,"cost":15.808,"seconds":7236.8,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":69.0693,"post":16779,"cost":20.363,"seconds":3621.8,"explorer":true}},"palomar__2026-08-24-000003":{"opus-5":{"status":"passed","score":59.5074,"post":11968,"cost":133.208,"seconds":23226.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":70.6726,"post":8668,"cost":211.181,"seconds":14049.6,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":47.3812,"post":15552,"cost":7.202,"seconds":2675.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":33.0187,"post":19797,"cost":53.402,"seconds":16643.4,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":27.047,"post":21562,"cost":5.756,"seconds":7855.5,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.724,"post":29342,"cost":7.214,"seconds":4295.3,"explorer":true},"opus-5.5":{"status":"passed","score":83.0424,"post":5012,"cost":10.837,"seconds":3043.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":66.7919,"post":9815,"cost":32.112,"seconds":4259.7,"explorer":true}},"palomar__2026-08-29-000011":{"opus-5":{"status":"passed","score":2.3024,"post":787840,"cost":38.489,"seconds":41338.6,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":4.6398,"post":768991,"cost":36.189,"seconds":4825.5,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":1.0206,"post":798177,"cost":24.143,"seconds":12897.2,"explorer":true},"muse-spark-1.3":{"status":"passed","score":3.0704,"post":781647,"cost":51.955,"seconds":26331.8,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":0.6748,"post":800965,"cost":3.491,"seconds":6747.8,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":806405,"cost":3.575,"seconds":5987.7,"explorer":null},"opus-5.5":{"status":"passed","score":23.2288,"post":619088,"cost":74.761,"seconds":38493.8,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":1.7801,"post":792052,"cost":9.312,"seconds":8180.9,"explorer":true}},"palomar__2026-08-29-000014":{"opus-5":{"status":"passed","score":42.0294,"post":24521,"cost":41.051,"seconds":37750.4,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":45.9136,"post":22878,"cost":197.141,"seconds":18163.2,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":22.3055,"post":32864,"cost":0.518,"seconds":7299.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":4.8725,"post":40238,"cost":11.643,"seconds":5737.0,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":18.4378,"post":34500,"cost":6.455,"seconds":11968.9,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0,"post":42299,"cost":0.57,"seconds":2175.9,"explorer":true},"opus-5.5":{"status":"passed","score":77.9167,"post":9341,"cost":16.842,"seconds":4130.5,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":56.3701,"post":18455,"cost":36.425,"seconds":6001.8,"explorer":true}},"palomar__2026-09-02-000014":{"opus-5":{"status":"passed","score":74.9608,"post":2394,"cost":54.376,"seconds":42248.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":74.511,"post":2437,"cost":75.267,"seconds":12984.4,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":25.5936,"post":7114,"cost":6.112,"seconds":2501.2,"explorer":true},"muse-spark-1.3":{"status":"passed","score":29.1183,"post":6777,"cost":8.21,"seconds":3311.8,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":22.3512,"post":7424,"cost":0.934,"seconds":2443.4,"explorer":true},"leanstral-1.5":{"status":"passed","score":2.3742,"post":9334,"cost":3.047,"seconds":1959.6,"explorer":true},"opus-5.5":{"status":"passed","score":80.2949,"post":1884,"cost":13.412,"seconds":5241.1,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":65.6417,"post":3285,"cost":21.079,"seconds":3080.4,"explorer":true}},"palomar__2026-09-01-000004":{"opus-5":{"status":"passed","score":52.3326,"post":28037,"cost":111.514,"seconds":40150.8,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":38.6157,"post":36105,"cost":187.644,"seconds":30533.8,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":30.6454,"post":40793,"cost":59.679,"seconds":33297.1,"explorer":true},"muse-spark-1.3":{"status":"passed","score":16.0138,"post":49399,"cost":56.554,"seconds":25375.5,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":7.9533,"post":54140,"cost":4.558,"seconds":6140.6,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.2244,"post":58686,"cost":9.348,"seconds":3629.5,"explorer":true},"opus-5.5":{"status":"passed","score":81.9545,"post":10614,"cost":58.43,"seconds":36434.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":40.8055,"post":34817,"cost":83.059,"seconds":12439.1,"explorer":true}},"palomar__2026-08-17-000002":{"opus-5":{"status":"passed","score":59.7626,"post":2034,"cost":12.771,"seconds":6473.7,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":49.9505,"post":2530,"cost":14.147,"seconds":4093.5,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":24.7082,"post":3806,"cost":8.671,"seconds":4512.6,"explorer":true},"muse-spark-1.3":{"status":"passed","score":37.9228,"post":3138,"cost":14.359,"seconds":6164.1,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":13.6696,"post":4364,"cost":0.829,"seconds":3536.4,"explorer":true},"leanstral-1.5":{"status":"passed","score":1.5232,"post":4978,"cost":2.881,"seconds":4616.6,"explorer":true},"opus-5.5":{"status":"passed","score":79.367,"post":1043,"cost":14.104,"seconds":14991.6,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":55.2918,"post":2260,"cost":6.636,"seconds":1831.7,"explorer":true}},"palomar__2026-08-29-000017":{"opus-5":{"status":"passed","score":14.21,"post":147286,"cost":27.166,"seconds":39244.9,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":22.0064,"post":133901,"cost":435.037,"seconds":38487.8,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":15.5555,"post":144976,"cost":83.11,"seconds":43211.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":8.4441,"post":157185,"cost":56.16,"seconds":38234.4,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":1.8377,"post":168527,"cost":1.214,"seconds":3134.1,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0,"post":171682,"cost":3.493,"seconds":3496.1,"explorer":true},"opus-5.5":{"status":"passed","score":61.2842,"post":66468,"cost":76.199,"seconds":39196.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":41.2425,"post":100876,"cost":210.667,"seconds":33636.2,"explorer":true}},"palomar__2026-09-03-000005":{"opus-5":{"status":"passed","score":56.9904,"post":16443,"cost":104.31,"seconds":38242.3,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":35.6726,"post":24593,"cost":143.933,"seconds":18486.3,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":29.3008,"post":27029,"cost":24.693,"seconds":10210.6,"explorer":true},"muse-spark-1.3":{"status":"passed","score":10.3581,"post":34271,"cost":10.344,"seconds":3434.3,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":12.0374,"post":33629,"cost":3.16,"seconds":4893.3,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.6042,"post":38000,"cost":9.84,"seconds":4638.5,"explorer":true},"opus-5.5":{"status":"passed","score":75.3315,"post":9431,"cost":30.979,"seconds":9966.3,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":11.5011,"post":33834,"cost":11.795,"seconds":4028.3,"explorer":true}},"palomar__2026-08-19-000003":{"opus-5":{"status":"passed","score":6.4107,"post":1587247,"cost":28.067,"seconds":41653.8,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":4.7712,"post":1615053,"cost":53.902,"seconds":10457.8,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":4.4969,"post":1619705,"cost":57.343,"seconds":16330.0,"explorer":true},"muse-spark-1.3":{"status":"passed","score":1.4256,"post":1671794,"cost":22.893,"seconds":23438.2,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":1.9567,"post":1662786,"cost":1.992,"seconds":7677.2,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0,"post":1695971,"cost":5.782,"seconds":3817.2,"explorer":true},"opus-5.5":{"status":"passed","score":19.8327,"post":1359615,"cost":13.708,"seconds":39641.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":21.5896,"post":1329817,"cost":221.334,"seconds":41474.6,"explorer":true}},"palomar__2026-09-03-000007":{"opus-5":{"status":"passed","score":71.25,"post":2185,"cost":72.215,"seconds":33338.5,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":30.2763,"post":5299,"cost":18.294,"seconds":2834.1,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":18.3289,"post":6207,"cost":7.349,"seconds":3735.3,"explorer":true},"muse-spark-1.3":{"status":"passed","score":11.8684,"post":6698,"cost":5.295,"seconds":2077.1,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":15.8026,"post":6399,"cost":1.075,"seconds":3024.4,"explorer":true},"leanstral-1.5":{"status":"passed","score":1.2632,"post":7504,"cost":6.163,"seconds":3816.8,"explorer":true},"opus-5.5":{"status":"passed","score":69.4342,"post":2323,"cost":6.361,"seconds":2223.5,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":50.9342,"post":3729,"cost":17.759,"seconds":3796.1,"explorer":true}},"palomar__2026-08-23-000001":{"opus-5":{"status":"passed","score":75.1777,"post":5551,"cost":78.236,"seconds":40177.4,"explorer":true},"gpt-5.6-sol":{"status":"failed","score":0.0,"post":18611,"cost":49.347,"seconds":2610.1,"explorer":null},"gemini-3.8-flash":{"status":"passed","score":23.8295,"post":17034,"cost":9.004,"seconds":4045.5,"explorer":true},"muse-spark-1.3":{"status":"passed","score":11.5414,"post":19782,"cost":15.017,"seconds":5456.8,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":11.6085,"post":19767,"cost":1.722,"seconds":4137.1,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.2057,"post":22317,"cost":5.2,"seconds":1934.9,"explorer":true},"opus-5.5":{"status":"passed","score":81.2324,"post":4197,"cost":7.312,"seconds":1962.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":12.6951,"post":19524,"cost":16.202,"seconds":5964.5,"explorer":true}},"palomar__2026-08-29-000006":{"opus-5":{"status":"passed","score":15.3354,"post":514811,"cost":44.326,"seconds":41654.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":3.7093,"post":585504,"cost":204.351,"seconds":30832.9,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":2.0062,"post":595860,"cost":35.878,"seconds":16386.4,"explorer":true},"muse-spark-1.3":{"status":"passed","score":7.8974,"post":560038,"cost":26.111,"seconds":20707.8,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":0.3128,"post":606157,"cost":3.782,"seconds":18325.3,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0072,"post":608015,"cost":8.012,"seconds":10042.0,"explorer":true},"opus-5.5":{"status":"passed","score":23.525,"post":465013,"cost":22.025,"seconds":39789.9,"explorer":null},"gpt-6.1-sol":{"status":"passed","score":20.5669,"post":483000,"cost":59.853,"seconds":17443.2,"explorer":true}},"palomar__2026-08-31-000008":{"opus-5":{"status":"passed","score":52.5895,"post":29944,"cost":134.006,"seconds":41816.4,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":27.5543,"post":45756,"cost":183.304,"seconds":16284.1,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":21.3224,"post":49692,"cost":42.778,"seconds":43208.2,"explorer":true},"muse-spark-1.3":{"status":"passed","score":9.9416,"post":56880,"cost":6.687,"seconds":4132.0,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":4.9225,"post":60050,"cost":2.11,"seconds":3399.2,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0459,"post":63130,"cost":4.727,"seconds":3402.5,"explorer":true},"opus-5.5":{"status":"passed","score":88.312,"post":7382,"cost":48.282,"seconds":21679.6,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":41.2989,"post":37075,"cost":70.983,"seconds":13279.9,"explorer":true}},"palomar__2026-08-27-000015":{"opus-5":{"status":"passed","score":53.6867,"post":2123,"cost":20.81,"seconds":4697.4,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":26.7234,"post":3359,"cost":21.911,"seconds":2828.3,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":24.2365,"post":3473,"cost":3.978,"seconds":1378.4,"explorer":true},"muse-spark-1.3":{"status":"passed","score":11.082,"post":4076,"cost":7.618,"seconds":3651.1,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":17.9974,"post":3759,"cost":0.657,"seconds":2166.1,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":4311,"cost":2.476,"seconds":2090.5,"explorer":null},"opus-5.5":{"status":"passed","score":58.8787,"post":1885,"cost":8.607,"seconds":3135.2,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":42.8665,"post":2619,"cost":7.157,"seconds":2002.2,"explorer":true}},"palomar__2026-08-22-000006":{"opus-5":{"status":"passed","score":26.9486,"post":143332,"cost":46.594,"seconds":41621.5,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":20.3866,"post":156207,"cost":168.02,"seconds":25350.7,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":18.8821,"post":159159,"cost":28.852,"seconds":12687.9,"explorer":true},"muse-spark-1.3":{"status":"passed","score":7.118,"post":182241,"cost":26.142,"seconds":25850.2,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":5.8418,"post":184745,"cost":3.131,"seconds":6061.1,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0352,"post":196138,"cost":1.938,"seconds":3003.0,"explorer":true},"opus-5.5":{"status":"passed","score":81.254,"post":36781,"cost":83.111,"seconds":37265.6,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":74.134,"post":50751,"cost":218.56,"seconds":37626.3,"explorer":true}},"palomar__2026-09-03-000004":{"opus-5":{"status":"passed","score":68.6756,"post":4158,"cost":70.248,"seconds":27450.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":40.9598,"post":7837,"cost":19.318,"seconds":4121.2,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":36.2664,"post":8460,"cost":4.2,"seconds":2118.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":34.7145,"post":8666,"cost":33.345,"seconds":16826.3,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":21.0411,"post":10481,"cost":2.354,"seconds":6683.5,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":10886,"cost":2.805,"seconds":757.2,"explorer":null},"opus-5.5":{"status":"passed","score":69.6926,"post":4023,"cost":15.078,"seconds":6934.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":59.1005,"post":5429,"cost":13.082,"seconds":2653.9,"explorer":true}},"palomar__2026-09-02-000001":{"opus-5":{"status":"passed","score":10.1802,"post":844336,"cost":55.619,"seconds":41087.8,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":0.8729,"post":931827,"cost":98.147,"seconds":9649.2,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":4.4654,"post":898057,"cost":78.818,"seconds":39495.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":3.2097,"post":909861,"cost":29.579,"seconds":34228.5,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":0.2207,"post":937958,"cost":2.986,"seconds":14968.5,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":939934,"cost":0.879,"seconds":1023.1,"explorer":null},"opus-5.5":{"status":"passed","score":14.0683,"post":807786,"cost":15.727,"seconds":37556.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":1.1941,"post":928808,"cost":18.973,"seconds":13167.7,"explorer":true}},"palomar__2026-08-29-000002":{"opus-5":{"status":"passed","score":46.0215,"post":419660,"cost":135.096,"seconds":39686.1,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":29.7427,"post":546221,"cost":183.563,"seconds":35278.0,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":15.9328,"post":653587,"cost":70.774,"seconds":43214.4,"explorer":true},"muse-spark-1.3":{"status":"passed","score":2.2867,"post":759680,"cost":5.732,"seconds":9914.4,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":2.6354,"post":756969,"cost":2.81,"seconds":13937.8,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0003,"post":777456,"cost":1.331,"seconds":1734.5,"explorer":true},"opus-5.5":{"status":"passed","score":74.0997,"post":201364,"cost":86.097,"seconds":40780.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":4.8746,"post":739560,"cost":21.674,"seconds":10618.6,"explorer":true}},"palomar__2026-08-20-000009":{"opus-5":{"status":"passed","score":21.628,"post":109452,"cost":110.622,"seconds":40818.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":19.1584,"post":112901,"cost":384.094,"seconds":30230.7,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":4.1716,"post":133831,"cost":10.358,"seconds":5567.2,"explorer":true},"muse-spark-1.3":{"status":"passed","score":3.8122,"post":134333,"cost":8.076,"seconds":4279.4,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":2.0629,"post":136776,"cost":3.303,"seconds":8124.5,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.169,"post":139421,"cost":5.956,"seconds":4333.9,"explorer":true},"opus-5.5":{"status":"passed","score":62.8196,"post":51925,"cost":66.214,"seconds":40764.2,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":4.7567,"post":133014,"cost":33.425,"seconds":19188.5,"explorer":true}},"palomar__2026-08-31-000014":{"opus-5":{"status":"passed","score":74.7831,"post":2441,"cost":126.499,"seconds":41651.5,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":47.6756,"post":5065,"cost":57.043,"seconds":5055.7,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":22.1281,"post":7538,"cost":5.69,"seconds":2798.7,"explorer":true},"muse-spark-1.3":{"status":"passed","score":13.9153,"post":8333,"cost":7.821,"seconds":3966.8,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":19.9897,"post":7745,"cost":2.304,"seconds":4974.1,"explorer":true},"leanstral-1.5":{"status":"passed","score":1.126,"post":9571,"cost":6.559,"seconds":3827.4,"explorer":true},"opus-5.5":{"status":"passed","score":73.2645,"post":2588,"cost":13.325,"seconds":4255.0,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":60.7955,"post":3795,"cost":15.464,"seconds":2653.1,"explorer":true}},"palomar__2026-08-22-000003":{"opus-5":{"status":"passed","score":72.8598,"post":5323,"cost":21.799,"seconds":4356.3,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":54.0917,"post":9004,"cost":44.304,"seconds":9295.8,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":38.2399,"post":12113,"cost":15.944,"seconds":6942.7,"explorer":true},"muse-spark-1.3":{"status":"passed","score":47.0555,"post":10384,"cost":18.532,"seconds":12568.9,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":26.1102,"post":14492,"cost":1.228,"seconds":2984.9,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.1836,"post":19577,"cost":0.868,"seconds":1143.4,"explorer":true},"opus-5.5":{"status":"passed","score":83.0674,"post":3321,"cost":8.406,"seconds":2666.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":69.872,"post":5909,"cost":16.489,"seconds":4994.8,"explorer":true}},"palomar__2026-08-28-000002":{"opus-5":{"status":"passed","score":90.9501,"post":722,"cost":40.035,"seconds":8017.7,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":92.2537,"post":618,"cost":20.077,"seconds":2004.6,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":72.7375,"post":2175,"cost":6.566,"seconds":3078.2,"explorer":true},"muse-spark-1.3":{"status":"passed","score":50.5014,"post":3949,"cost":4.266,"seconds":1685.5,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":48.7466,"post":4089,"cost":1.633,"seconds":3733.7,"explorer":true},"leanstral-1.5":{"status":"passed","score":3.9734,"post":7661,"cost":2.29,"seconds":1066.5,"explorer":true},"opus-5.5":{"status":"passed","score":91.5768,"post":672,"cost":4.887,"seconds":1383.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":91.2635,"post":697,"cost":7.113,"seconds":1669.5,"explorer":true}},"palomar__2026-09-02-000003":{"opus-5":{"status":"passed","score":64.4097,"post":17425,"cost":159.941,"seconds":39960.3,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":24.3464,"post":37040,"cost":58.793,"seconds":3800.4,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":28.9297,"post":34796,"cost":21.385,"seconds":12035.7,"explorer":true},"muse-spark-1.3":{"status":"passed","score":11.7953,"post":43185,"cost":6.121,"seconds":3199.6,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":18.1311,"post":40083,"cost":3.104,"seconds":6067.7,"explorer":true},"leanstral-1.5":{"status":"passed","score":6.1417,"post":45953,"cost":2.406,"seconds":1354.8,"explorer":true},"opus-5.5":{"status":"passed","score":88.0678,"post":5842,"cost":23.519,"seconds":22595.7,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":12.4265,"post":42876,"cost":4.896,"seconds":2643.9,"explorer":true}},"palomar__2026-09-01-000009":{"opus-5":{"status":"passed","score":45.5501,"post":48786,"cost":37.991,"seconds":41814.4,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":58.4868,"post":37195,"cost":702.039,"seconds":37739.4,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":39.0087,"post":54647,"cost":53.882,"seconds":27698.3,"explorer":true},"muse-spark-1.3":{"status":"passed","score":17.1756,"post":74209,"cost":86.638,"seconds":43154.2,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":14.6778,"post":76447,"cost":1.462,"seconds":2452.3,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.5368,"post":89117,"cost":6.137,"seconds":5347.6,"explorer":true},"opus-5.5":{"status":"passed","score":99.1529,"post":759,"cost":6.188,"seconds":2115.7,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":98.0703,"post":1729,"cost":6.014,"seconds":1342.8,"explorer":true}},"palomar__2026-08-22-000010":{"opus-5":{"status":"passed","score":20.4027,"post":501992,"cost":25.007,"seconds":41272.7,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":19.7832,"post":505899,"cost":102.687,"seconds":11371.9,"explorer":true},"gemini-3.8-flash":{"status":"failed","score":0.0,"post":522754,"cost":19.828,"seconds":43212.3,"explorer":null},"muse-spark-1.3":{"status":"failed","score":0.0,"post":539207,"cost":40.871,"seconds":24024.7,"explorer":null},"gpt-5.6-luna":{"status":"passed","score":1.3898,"post":621900,"cost":2.173,"seconds":12127.3,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0,"post":630665,"cost":2.583,"seconds":1164.9,"explorer":true},"opus-5.5":{"status":"passed","score":47.5936,"post":330509,"cost":73.266,"seconds":39648.3,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":23.9408,"post":479679,"cost":42.869,"seconds":11479.3,"explorer":true}},"palomar__2026-08-31-000005":{"opus-5":{"status":"passed","score":9.8179,"post":359493,"cost":23.035,"seconds":40862.5,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":17.4485,"post":329075,"cost":345.165,"seconds":36094.7,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":7.9841,"post":366803,"cost":27.047,"seconds":17283.1,"explorer":true},"muse-spark-1.3":{"status":"passed","score":7.5619,"post":368486,"cost":18.368,"seconds":17757.1,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":1.2503,"post":393646,"cost":3.605,"seconds":12847.1,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0083,"post":398597,"cost":3.322,"seconds":2874.4,"explorer":true},"opus-5.5":{"status":"passed","score":31.5797,"post":272744,"cost":45.452,"seconds":33314.0,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":9.1167,"post":362288,"cost":14.733,"seconds":8356.0,"explorer":true}},"palomar__2026-09-01-000007":{"opus-5":{"status":"passed","score":72.622,"post":3831,"cost":62.22,"seconds":25587.2,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":95.4906,"post":631,"cost":136.999,"seconds":14035.1,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":24.9625,"post":10500,"cost":4.094,"seconds":1823.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":15.8937,"post":11769,"cost":8.661,"seconds":3437.9,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":18.2163,"post":11444,"cost":1.302,"seconds":2977.1,"explorer":true},"leanstral-1.5":{"status":"passed","score":1.5722,"post":13773,"cost":2.764,"seconds":859.5,"explorer":true},"opus-5.5":{"status":"passed","score":73.694,"post":3681,"cost":14.447,"seconds":4139.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":50.2537,"post":6961,"cost":9.788,"seconds":2548.6,"explorer":true}},"palomar__2026-09-02-000004":{"opus-5":{"status":"passed","score":9.541,"post":134613,"cost":10.14,"seconds":8399.5,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":19.9038,"post":119192,"cost":445.647,"seconds":34033.3,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":7.1984,"post":138099,"cost":25.623,"seconds":14848.6,"explorer":true},"muse-spark-1.3":{"status":"passed","score":5.0151,"post":141348,"cost":15.335,"seconds":22217.0,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":4.4372,"post":142208,"cost":3.038,"seconds":5672.4,"explorer":true},"leanstral-1.5":{"status":"passed","score":-0.0591,"post":148899,"cost":6.065,"seconds":6395.0,"explorer":true},"opus-5.5":{"status":"passed","score":61.2468,"post":57669,"cost":85.729,"seconds":37530.0,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":1.3386,"post":146819,"cost":8.463,"seconds":5163.9,"explorer":true}},"palomar__2026-08-29-000015":{"opus-5":{"status":"passed","score":74.1168,"post":1905,"cost":59.871,"seconds":20968.8,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":61.9158,"post":2803,"cost":82.714,"seconds":12995.0,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":26.6712,"post":5397,"cost":3.95,"seconds":2452.9,"explorer":true},"muse-spark-1.3":{"status":"passed","score":19.3342,"post":5937,"cost":3.48,"seconds":2427.3,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":24.769,"post":5537,"cost":0.933,"seconds":2947.6,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.6522,"post":7312,"cost":23.433,"seconds":4502.4,"explorer":true},"opus-5.5":{"status":"passed","score":81.0734,"post":1393,"cost":14.03,"seconds":4619.2,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":55.9918,"post":3239,"cost":13.523,"seconds":3179.8,"explorer":true}},"palomar__2026-08-26-000006":{"opus-5":{"status":"passed","score":58.5996,"post":14344,"cost":132.917,"seconds":40106.7,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":41.7583,"post":20179,"cost":100.997,"seconds":18867.9,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":7.2705,"post":32128,"cost":9.152,"seconds":2487.5,"explorer":true},"muse-spark-1.3":{"status":"passed","score":6.3353,"post":32452,"cost":13.421,"seconds":2569.5,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":7.1521,"post":32169,"cost":1.875,"seconds":3529.4,"explorer":true},"leanstral-1.5":{"status":"missing","score":null,"post":null,"cost":3.126,"seconds":1126.0,"explorer":null},"opus-5.5":{"status":"passed","score":87.9037,"post":4191,"cost":12.484,"seconds":4179.6,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":47.1989,"post":18294,"cost":35.228,"seconds":7275.7,"explorer":true}},"palomar__2026-09-03-000002":{"opus-5":{"status":"passed","score":11.236,"post":510400,"cost":26.852,"seconds":29880.4,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":12.1494,"post":505148,"cost":107.235,"seconds":7489.5,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":11.6313,"post":508127,"cost":38.374,"seconds":43210.9,"explorer":true},"muse-spark-1.3":{"status":"passed","score":3.0356,"post":557553,"cost":19.449,"seconds":14956.5,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":0.1598,"post":574089,"cost":2.23,"seconds":4286.2,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0203,"post":574891,"cost":2.564,"seconds":1207.0,"explorer":true},"opus-5.5":{"status":"passed","score":29.9043,"post":403056,"cost":68.551,"seconds":35789.9,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":15.7836,"post":484251,"cost":38.229,"seconds":7165.6,"explorer":true}},"palomar__2026-09-02-000011":{"opus-5":{"status":"passed","score":32.8065,"post":139620,"cost":154.557,"seconds":41876.7,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":21.4045,"post":163312,"cost":256.414,"seconds":21382.1,"explorer":true},"gemini-3.8-flash":{"status":"failed","score":0.0,"post":171469,"cost":90.564,"seconds":43210.5,"explorer":null},"muse-spark-1.3":{"status":"passed","score":6.1991,"post":194907,"cost":19.705,"seconds":13544.1,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":3.3476,"post":200832,"cost":4.345,"seconds":6696.9,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.0313,"post":207723,"cost":7.31,"seconds":7765.2,"explorer":true},"opus-5.5":{"status":"passed","score":66.6665,"post":69263,"cost":88.381,"seconds":28889.5,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":47.8935,"post":108271,"cost":227.025,"seconds":27550.5,"explorer":true}},"palomar__2026-09-01-000008":{"opus-5":{"status":"passed","score":72.0987,"post":1142,"cost":50.768,"seconds":15034.4,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":54.6054,"post":1858,"cost":17.815,"seconds":4021.2,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":20.8405,"post":3240,"cost":2.387,"seconds":1082.7,"explorer":true},"muse-spark-1.3":{"status":"passed","score":11.5075,"post":3622,"cost":3.765,"seconds":2093.3,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":31.1019,"post":2820,"cost":0.849,"seconds":2382.7,"explorer":true},"leanstral-1.5":{"status":"failed","score":0.0,"post":3833,"cost":0.941,"seconds":910.5,"explorer":null},"opus-5.5":{"status":"passed","score":71.83,"post":1153,"cost":5.437,"seconds":1910.7,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":60.0782,"post":1634,"cost":4.441,"seconds":1496.9,"explorer":true}},"palomar__2026-09-02-000006":{"opus-5":{"status":"passed","score":14.3016,"post":355304,"cost":24.668,"seconds":42067.1,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":11.9858,"post":364905,"cost":243.022,"seconds":41098.6,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":1.6098,"post":407924,"cost":9.829,"seconds":4846.5,"explorer":true},"muse-spark-1.3":{"status":"passed","score":1.6433,"post":407785,"cost":12.86,"seconds":11546.8,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":0.5803,"post":412192,"cost":3.115,"seconds":10798.0,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.3309,"post":413226,"cost":2.988,"seconds":3578.2,"explorer":true},"opus-5.5":{"status":"passed","score":44.1343,"post":231618,"cost":92.241,"seconds":39925.5,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":2.3669,"post":404785,"cost":18.098,"seconds":13007.1,"explorer":true}},"palomar__2026-08-20-000008":{"opus-5":{"status":"passed","score":47.2285,"post":15004,"cost":85.029,"seconds":39669.3,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":36.779,"post":17975,"cost":173.775,"seconds":17851.0,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":12.2995,"post":24935,"cost":6.809,"seconds":4045.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":17.5999,"post":23428,"cost":13.513,"seconds":5365.6,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":9.011,"post":25870,"cost":2.53,"seconds":4911.4,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.204,"post":28374,"cost":6.26,"seconds":3297.1,"explorer":true},"opus-5.5":{"status":"passed","score":80.4903,"post":5547,"cost":36.198,"seconds":14268.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":2.8876,"post":27611,"cost":7.206,"seconds":5614.9,"explorer":true}},"palomar__2026-09-04-000005":{"opus-5":{"status":"passed","score":39.0762,"post":41416,"cost":98.826,"seconds":39365.3,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":27.945,"post":48983,"cost":144.206,"seconds":22912.5,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":6.7858,"post":63367,"cost":14.471,"seconds":43203.9,"explorer":true},"muse-spark-1.3":{"status":"passed","score":10.509,"post":60836,"cost":48.06,"seconds":20692.3,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":2.9538,"post":65972,"cost":2.425,"seconds":3685.3,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.075,"post":67929,"cost":3.895,"seconds":4866.9,"explorer":true},"opus-5.5":{"status":"failed","score":0.0,"post":21341,"cost":30.609,"seconds":15797.1,"explorer":null},"gpt-6.1-sol":{"status":"passed","score":34.3116,"post":44655,"cost":57.16,"seconds":11498.9,"explorer":true}},"palomar__2026-09-01-000011":{"opus-5":{"status":"passed","score":94.3358,"post":452,"cost":88.87,"seconds":24889.7,"explorer":true},"gpt-5.6-sol":{"status":"passed","score":88.8471,"post":890,"cost":21.527,"seconds":2575.4,"explorer":true},"gemini-3.8-flash":{"status":"passed","score":25.5764,"post":5939,"cost":5.028,"seconds":2602.8,"explorer":true},"muse-spark-1.3":{"status":"passed","score":16.4035,"post":6671,"cost":22.47,"seconds":6233.7,"explorer":true},"gpt-5.6-luna":{"status":"passed","score":20.802,"post":6320,"cost":1.419,"seconds":4491.6,"explorer":true},"leanstral-1.5":{"status":"passed","score":0.3885,"post":7949,"cost":5.262,"seconds":2027.1,"explorer":true},"opus-5.5":{"status":"passed","score":93.5338,"post":516,"cost":3.811,"seconds":1340.4,"explorer":true},"gpt-6.1-sol":{"status":"passed","score":91.7544,"post":658,"cost":3.295,"seconds":714.2,"explorer":true}}},"logos":{"anthropic":"<svg fill=\"currentColor\" fill-rule=\"evenodd\" viewBox=\"0 0 24 24\" xmlns=\"http://www.w3.org/2000/svg\"><path d=\"M13.827 3.52h3.603L24 20h-3.603l-6.57-16.48zm-7.258 0h3.767L16.906 20h-3.674l-1.343-3.461H5.017l-1.344 3.46H0L6.57 3.522zm4.132 9.959L8.453 7.687 6.205 13.48H10.7z\"></path></svg>","gemini":"<svg viewBox=\"0 0 24 24\" xmlns=\"http://www.w3.org/2000/svg\"><path d=\"M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z\" fill=\"#3186FF\"></path><path d=\"M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z\" fill=\"url(#lobe-icons-gemini-0-_R_0_)\"></path><path d=\"M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z\" fill=\"url(#lobe-icons-gemini-1-_R_0_)\"></path><path d=\"M20.616 10.835a14.147 14.147 0 01-4.45-3.001 14.111 14.111 0 01-3.678-6.452.503.503 0 00-.975 0 14.134 14.134 0 01-3.679 6.452 14.155 14.155 0 01-4.45 3.001c-.65.28-1.318.505-2.002.678a.502.502 0 000 .975c.684.172 1.35.397 2.002.677a14.147 14.147 0 014.45 3.001 14.112 14.112 0 013.679 6.453.502.502 0 00.975 0c.172-.685.397-1.351.677-2.003a14.145 14.145 0 013.001-4.45 14.113 14.113 0 016.453-3.678.503.503 0 000-.975 13.245 13.245 0 01-2.003-.678z\" fill=\"url(#lobe-icons-gemini-2-_R_0_)\"></path><defs><linearGradient gradientUnits=\"userSpaceOnUse\" id=\"lobe-icons-gemini-0-_R_0_\" x1=\"7\" x2=\"11\" y1=\"15.5\" y2=\"12\"><stop stop-color=\"#08B962\"></stop><stop offset=\"1\" stop-color=\"#08B962\" stop-opacity=\"0\"></stop></linearGradient><linearGradient gradientUnits=\"userSpaceOnUse\" id=\"lobe-icons-gemini-1-_R_0_\" x1=\"8\" x2=\"11.5\" y1=\"5.5\" y2=\"11\"><stop stop-color=\"#F94543\"></stop><stop offset=\"1\" stop-color=\"#F94543\" stop-opacity=\"0\"></stop></linearGradient><linearGradient gradientUnits=\"userSpaceOnUse\" id=\"lobe-icons-gemini-2-_R_0_\" x1=\"3.5\" x2=\"17.5\" y1=\"13.5\" y2=\"12\"><stop stop-color=\"#FABC12\"></stop><stop offset=\".46\" stop-color=\"#FABC12\" stop-opacity=\"0\"></stop></linearGradient></defs></svg>","meta":"<svg fill=\"#0467DF\" role=\"img\" viewBox=\"0 0 24 24\" xmlns=\"http://www.w3.org/2000/svg\"><path d=\"M6.915 4.03c-1.968 0-3.683 1.28-4.871 3.113C.704 9.208 0 11.883 0 14.449c0 .706.07 1.369.21 1.973a6.624 6.624 0 0 0 .265.86 5.297 5.297 0 0 0 .371.761c.696 1.159 1.818 1.927 3.593 1.927 1.497 0 2.633-.671 3.965-2.444.76-1.012 1.144-1.626 2.663-4.32l.756-1.339.186-.325c.061.1.121.196.183.3l2.152 3.595c.724 1.21 1.665 2.556 2.47 3.314 1.046.987 1.992 1.22 3.06 1.22 1.075 0 1.876-.355 2.455-.843a3.743 3.743 0 0 0 .81-.973c.542-.939.861-2.127.861-3.745 0-2.72-.681-5.357-2.084-7.45-1.282-1.912-2.957-2.93-4.716-2.93-1.047 0-2.088.467-3.053 1.308-.652.57-1.257 1.29-1.82 2.05-.69-.875-1.335-1.547-1.958-2.056-1.182-.966-2.315-1.303-3.454-1.303zm10.16 2.053c1.147 0 2.188.758 2.992 1.999 1.132 1.748 1.647 4.195 1.647 6.4 0 1.548-.368 2.9-1.839 2.9-.58 0-1.027-.23-1.664-1.004-.496-.601-1.343-1.878-2.832-4.358l-.617-1.028a44.908 44.908 0 0 0-1.255-1.98c.07-.109.141-.224.211-.327 1.12-1.667 2.118-2.602 3.358-2.602zm-10.201.553c1.265 0 2.058.791 2.675 1.446.307.327.737.871 1.234 1.579l-1.02 1.566c-.757 1.163-1.882 3.017-2.837 4.338-1.191 1.649-1.81 1.817-2.486 1.817-.524 0-1.038-.237-1.383-.794-.263-.426-.464-1.13-.464-2.046 0-2.221.63-4.535 1.66-6.088.454-.687.964-1.226 1.533-1.533a2.264 2.264 0 0 1 1.088-.285z\"/></svg>","mistral":"<svg viewBox=\"0 0 24 24\" xmlns=\"http://www.w3.org/2000/svg\"><path d=\"M3.428 3.4h3.429v3.428H3.428V3.4zm13.714 0h3.43v3.428h-3.43V3.4z\" fill=\"gold\"></path><path d=\"M3.428 6.828h6.857v3.429H3.429V6.828zm10.286 0h6.857v3.429h-6.857V6.828z\" fill=\"#FFAF00\"></path><path d=\"M3.428 10.258h17.144v3.428H3.428v-3.428z\" fill=\"#FF8205\"></path><path d=\"M3.428 13.686h3.429v3.428H3.428v-3.428zm6.858 0h3.429v3.428h-3.429v-3.428zm6.856 0h3.43v3.428h-3.43v-3.428z\" fill=\"#FA500F\"></path><path d=\"M0 17.114h10.286v3.429H0v-3.429zm13.714 0H24v3.429H13.714v-3.429z\" fill=\"#E10500\"></path></svg>","openai":"<svg fill=\"currentColor\" fill-rule=\"evenodd\" viewBox=\"0 0 24 24\" xmlns=\"http://www.w3.org/2000/svg\"><path d=\"M9.205 8.658v-2.26c0-.19.072-.333.238-.428l4.543-2.616c.619-.357 1.356-.523 2.117-.523 2.854 0 4.662 2.212 4.662 4.566 0 .167 0 .357-.024.547l-4.71-2.759a.797.797 0 00-.856 0l-5.97 3.473zm10.609 8.8V12.06c0-.333-.143-.57-.429-.737l-5.97-3.473 1.95-1.118a.433.433 0 01.476 0l4.543 2.617c1.309.76 2.189 2.378 2.189 3.948 0 1.808-1.07 3.473-2.76 4.163zM7.802 12.703l-1.95-1.142c-.167-.095-.239-.238-.239-.428V5.899c0-2.545 1.95-4.472 4.591-4.472 1 0 1.927.333 2.712.928L8.23 5.067c-.285.166-.428.404-.428.737v6.898zM12 15.128l-2.795-1.57v-3.33L12 8.658l2.795 1.57v3.33L12 15.128zm1.796 7.23c-1 0-1.927-.332-2.712-.927l4.686-2.712c.285-.166.428-.404.428-.737v-6.898l1.974 1.142c.167.095.238.238.238.428v5.233c0 2.545-1.974 4.472-4.614 4.472zm-5.637-5.303l-4.544-2.617c-1.308-.761-2.188-2.378-2.188-3.948A4.482 4.482 0 014.21 6.327v5.423c0 .333.143.571.428.738l5.947 3.449-1.95 1.118a.432.432 0 01-.476 0zm-.262 3.9c-2.688 0-4.662-2.021-4.662-4.519 0-.19.024-.38.047-.57l4.686 2.71c.286.167.571.167.856 0l5.97-3.448v2.26c0 .19-.07.333-.237.428l-4.543 2.616c-.619.357-1.356.523-2.117.523zm5.899 2.83a5.947 5.947 0 005.827-4.756C22.287 18.339 24 15.84 24 13.296c0-1.665-.713-3.282-1.998-4.448.119-.5.19-.999.19-1.498 0-3.401-2.759-5.947-5.946-5.947-.642 0-1.26.095-1.88.31A5.962 5.962 0 0010.205 0a5.947 5.947 0 00-5.827 4.757C1.713 5.447 0 7.945 0 10.49c0 1.666.713 3.283 1.998 4.448-.119.5-.19 1-.19 1.499 0 3.401 2.759 5.946 5.946 5.946.642 0 1.26-.095 1.88-.309a5.96 5.96 0 004.162 1.713z\"></path></svg>"}}