{"providers":"claude+google+openai","ladder":{"0":{"provider":"openai","model":"gpt-5.6-luna","effort":"low","score":1155.6,"price":0.0072},"1":{"provider":"openai","model":"gpt-5.6-luna","effort":"medium","score":1274.5,"price":0.0133},"2":{"provider":"openai","model":"gpt-5.6-luna","effort":"high","score":1465.8,"price":0.0412},"3":{"provider":"openai","model":"gpt-5.6-luna","effort":"xhigh","score":1525.7,"price":0.0667},"4":{"provider":"openai","model":"gpt-5.6-luna","effort":"max","score":1578.3,"price":0.1022},"5":{"provider":"claude","model":"claude-opus-5","effort":"medium","score":1619.6,"price":1.3641},"6":{"provider":"openai","model":"gpt-5.6-sol","effort":"high","score":1621.2,"price":1.3708},"7":{"provider":"openai","model":"gpt-5.6-sol","effort":"xhigh","score":1678.9,"price":2.1141},"8":{"provider":"claude","model":"claude-opus-5","effort":"high","score":1732.8,"price":3.0271},"9":{"provider":"claude","model":"claude-opus-5","effort":"xhigh","score":1813.8,"price":4.963},"10":{"provider":"claude","model":"claude-opus-5","effort":"max","score":1844.7,"price":6.766}},"ladders":{"claude":{"0":{"provider":"claude","model":"claude-haiku-4-5-20251001","effort":"","score":913.5,"price":0.1907},"1":{"provider":"claude","model":"claude-haiku-4-5-20251001","effort":"","score":913.5,"price":0.1907},"2":{"provider":"claude","model":"claude-opus-5","effort":"low","score":1457.4,"price":0.5817},"3":{"provider":"claude","model":"claude-opus-5","effort":"low","score":1457.4,"price":0.5817},"4":{"provider":"claude","model":"claude-opus-5","effort":"medium","score":1619.6,"price":1.3641},"5":{"provider":"claude","model":"claude-opus-5","effort":"medium","score":1619.6,"price":1.3641},"6":{"provider":"claude","model":"claude-opus-5","effort":"high","score":1732.8,"price":3.0271},"7":{"provider":"claude","model":"claude-opus-5","effort":"high","score":1732.8,"price":3.0271},"8":{"provider":"claude","model":"claude-opus-5","effort":"xhigh","score":1813.8,"price":4.963},"9":{"provider":"claude","model":"claude-opus-5","effort":"xhigh","score":1813.8,"price":4.963},"10":{"provider":"claude","model":"claude-opus-5","effort":"max","score":1844.7,"price":6.766}},"openai":{"0":{"provider":"openai","model":"gpt-5.6-luna","effort":"low","score":1155.6,"price":0.0072},"1":{"provider":"openai","model":"gpt-5.6-luna","effort":"medium","score":1274.5,"price":0.0133},"2":{"provider":"openai","model":"gpt-5.6-luna","effort":"medium","score":1274.5,"price":0.0133},"3":{"provider":"openai","model":"gpt-5.6-luna","effort":"high","score":1465.8,"price":0.0412},"4":{"provider":"openai","model":"gpt-5.6-luna","effort":"xhigh","score":1525.7,"price":0.0667},"5":{"provider":"openai","model":"gpt-5.6-luna","effort":"xhigh","score":1525.7,"price":0.0667},"6":{"provider":"openai","model":"gpt-5.6-luna","effort":"max","score":1578.3,"price":0.1022},"7":{"provider":"openai","model":"gpt-5.6-sol","effort":"high","score":1621.2,"price":1.3708},"8":{"provider":"openai","model":"gpt-5.6-sol","effort":"xhigh","score":1678.9,"price":2.1141},"9":{"provider":"openai","model":"gpt-5.6-sol","effort":"xhigh","score":1678.9,"price":2.1141},"10":{"provider":"openai","model":"gpt-5.6-sol","effort":"max","score":1723,"price":3.4935}},"claude+openai":{"0":{"provider":"openai","model":"gpt-5.6-luna","effort":"low","score":1155.6,"price":0.0072},"1":{"provider":"openai","model":"gpt-5.6-luna","effort":"medium","score":1274.5,"price":0.0133},"2":{"provider":"openai","model":"gpt-5.6-luna","effort":"high","score":1465.8,"price":0.0412},"3":{"provider":"openai","model":"gpt-5.6-luna","effort":"xhigh","score":1525.7,"price":0.0667},"4":{"provider":"openai","model":"gpt-5.6-luna","effort":"max","score":1578.3,"price":0.1022},"5":{"provider":"claude","model":"claude-opus-5","effort":"medium","score":1619.6,"price":1.3641},"6":{"provider":"openai","model":"gpt-5.6-sol","effort":"high","score":1621.2,"price":1.3708},"7":{"provider":"openai","model":"gpt-5.6-sol","effort":"xhigh","score":1678.9,"price":2.1141},"8":{"provider":"claude","model":"claude-opus-5","effort":"high","score":1732.8,"price":3.0271},"9":{"provider":"claude","model":"claude-opus-5","effort":"xhigh","score":1813.8,"price":4.963},"10":{"provider":"claude","model":"claude-opus-5","effort":"max","score":1844.7,"price":6.766}},"google":{"0":{"provider":"google","model":"gemini-3.7-flash-low","effort":"","score":1452.2,"price":0.391},"1":{"provider":"google","model":"gemini-3.7-flash-low","effort":"","score":1452.2,"price":0.391},"2":{"provider":"google","model":"gemini-3.7-flash-low","effort":"","score":1452.2,"price":0.391},"3":{"provider":"google","model":"gemini-3.7-flash-medium","effort":"","score":1498.3,"price":0.7622},"4":{"provider":"google","model":"gemini-3.7-flash-medium","effort":"","score":1498.3,"price":0.7622},"5":{"provider":"google","model":"gemini-3.7-flash-medium","effort":"","score":1498.3,"price":0.7622},"6":{"provider":"google","model":"gemini-3.7-flash-medium","effort":"","score":1498.3,"price":0.7622},"7":{"provider":"google","model":"gemini-3.7-flash-medium","effort":"","score":1498.3,"price":0.7622},"8":{"provider":"google","model":"gemini-3.7-flash-high","effort":"","score":1531.5,"price":1.2478},"9":{"provider":"google","model":"gemini-3.7-flash-high","effort":"","score":1531.5,"price":1.2478},"10":{"provider":"google","model":"gemini-3.7-flash-high","effort":"","score":1531.5,"price":1.2478}},"claude+google":{"0":{"provider":"claude","model":"claude-haiku-4-5-20251001","effort":"","score":913.5,"price":0.1907},"1":{"provider":"google","model":"gemini-3.7-flash-low","effort":"","score":1452.2,"price":0.391},"2":{"provider":"claude","model":"claude-opus-5","effort":"low","score":1457.4,"price":0.5817},"3":{"provider":"claude","model":"claude-opus-5","effort":"low","score":1457.4,"price":0.5817},"4":{"provider":"google","model":"gemini-3.7-flash-medium","effort":"","score":1498.3,"price":0.7622},"5":{"provider":"google","model":"gemini-3.7-flash-high","effort":"","score":1531.5,"price":1.2478},"6":{"provider":"claude","model":"claude-opus-5","effort":"medium","score":1619.6,"price":1.3641},"7":{"provider":"claude","model":"claude-opus-5","effort":"high","score":1732.8,"price":3.0271},"8":{"provider":"claude","model":"claude-opus-5","effort":"high","score":1732.8,"price":3.0271},"9":{"provider":"claude","model":"claude-opus-5","effort":"xhigh","score":1813.8,"price":4.963},"10":{"provider":"claude","model":"claude-opus-5","effort":"max","score":1844.7,"price":6.766}},"google+openai":{"0":{"provider":"openai","model":"gpt-5.6-luna","effort":"low","score":1155.6,"price":0.0072},"1":{"provider":"openai","model":"gpt-5.6-luna","effort":"medium","score":1274.5,"price":0.0133},"2":{"provider":"openai","model":"gpt-5.6-luna","effort":"medium","score":1274.5,"price":0.0133},"3":{"provider":"openai","model":"gpt-5.6-luna","effort":"high","score":1465.8,"price":0.0412},"4":{"provider":"openai","model":"gpt-5.6-luna","effort":"xhigh","score":1525.7,"price":0.0667},"5":{"provider":"openai","model":"gpt-5.6-luna","effort":"xhigh","score":1525.7,"price":0.0667},"6":{"provider":"openai","model":"gpt-5.6-luna","effort":"max","score":1578.3,"price":0.1022},"7":{"provider":"openai","model":"gpt-5.6-sol","effort":"high","score":1621.2,"price":1.3708},"8":{"provider":"openai","model":"gpt-5.6-sol","effort":"xhigh","score":1678.9,"price":2.1141},"9":{"provider":"openai","model":"gpt-5.6-sol","effort":"xhigh","score":1678.9,"price":2.1141},"10":{"provider":"openai","model":"gpt-5.6-sol","effort":"max","score":1723,"price":3.4935}},"claude+google+openai":{"0":{"provider":"openai","model":"gpt-5.6-luna","effort":"low","score":1155.6,"price":0.0072},"1":{"provider":"openai","model":"gpt-5.6-luna","effort":"medium","score":1274.5,"price":0.0133},"2":{"provider":"openai","model":"gpt-5.6-luna","effort":"high","score":1465.8,"price":0.0412},"3":{"provider":"openai","model":"gpt-5.6-luna","effort":"xhigh","score":1525.7,"price":0.0667},"4":{"provider":"openai","model":"gpt-5.6-luna","effort":"max","score":1578.3,"price":0.1022},"5":{"provider":"claude","model":"claude-opus-5","effort":"medium","score":1619.6,"price":1.3641},"6":{"provider":"openai","model":"gpt-5.6-sol","effort":"high","score":1621.2,"price":1.3708},"7":{"provider":"openai","model":"gpt-5.6-sol","effort":"xhigh","score":1678.9,"price":2.1141},"8":{"provider":"claude","model":"claude-opus-5","effort":"high","score":1732.8,"price":3.0271},"9":{"provider":"claude","model":"claude-opus-5","effort":"xhigh","score":1813.8,"price":4.963},"10":{"provider":"claude","model":"claude-opus-5","effort":"max","score":1844.7,"price":6.766}}},"runs":{"0":"codex app-server · turn/start { model: \"gpt-5.6-luna\", effort: \"low\" }","1":"codex app-server · turn/start { model: \"gpt-5.6-luna\", effort: \"medium\" }","2":"codex app-server · turn/start { model: \"gpt-5.6-luna\", effort: \"high\" }","3":"codex app-server · turn/start { model: \"gpt-5.6-luna\", effort: \"xhigh\" }","4":"codex app-server · turn/start { model: \"gpt-5.6-luna\", effort: \"max\" }","5":"claude -p --model claude-opus-5 --effort medium","6":"codex app-server · turn/start { model: \"gpt-5.6-sol\", effort: \"high\" }","7":"codex app-server · turn/start { model: \"gpt-5.6-sol\", effort: \"xhigh\" }","8":"claude -p --model claude-opus-5 --effort high","9":"claude -p --model claude-opus-5 --effort xhigh","10":"claude -p --model claude-opus-5 --effort max"},"plotted":33,"skipped":[],"source":{"benchmark":"GDPval-AA v2, Artificial Analysis","url":"https://artificialanalysis.ai/evaluations/gdpval-aa","score":"Elo from blind pairwise judging of complete work deliverables over 220 GDPval tasks in an agentic harness, anchored so a human expert scores 1000. 95% CIs run about +/-15 to +/-27, so gaps under ~35 Elo are not separable.","price":"USD per GDPval task, as Artificial Analysis measured it on the same runs.","captured":"2026-08-20","database":"https://github.com/teamofsilicons/omnipotent/blob/main/models-gdpval.json"},"caveats":["Left out because Artificial Analysis has no GDPval-AA v2 score for them: gpt-5.3-codex-spark, gemini-3.1-pro-high/low (only a Preview build is scored), claude-opus-4-6-thinking, gpt-oss-120b-medium (only high and low are scored), gemini-3.6-flash and gemini-3.5-flash below high.","Left out because AA scores them but publishes no cost: claude-sonnet-5 below max effort.","claude-fable-5 is left out: AA's only Fable 5 row is a router that can serve Claude Opus 4.8, so its Elo does not describe what `claude --model claude-fable-5` runs.","claude-sonnet-4-6 through agy is left out: AA measured it at max effort and agy exposes no effort control, so the score may not describe what the CLI runs.","claude-haiku-4-5-20251001 carries no effort because AA scored one 'Reasoning' configuration with no effort split.","Gemini prices are promotional through 2026-12-31 and double on 2027-01-01, which will move those points right. AA also measured Gemini through Google's own API, not through agy.","AA bills OpenAI cache writes at 1.25x input, which OpenAI's own rate card does not charge, so GPT-5.6 costs run about 3% high. It is applied consistently, so the ordering is unaffected."],"fresh":true}