Acropolis

GPT-5.1 Codex mini

OpenAIGrade B. Evidence grade B of A to D: good.ProprietaryReleased 13 Nov 2025
Compare with peers

Benchmark appearances

Best verified run per board, with confidence intervals and Pareto frontier status.

BenchmarkRankScoreCostStatusObserved
Terminal Bench

Epoch AI Benchmarking Hub · hookele

#46 / 202
61.6%[57.9% to 65.3%]UnknownStandard12 Nov 2025
Terminal Bench

Epoch AI Benchmarking Hub · Crux

#88 / 202
43.1%[37.3% to 49%]UnknownStandard12 Nov 2025
Terminal Bench

Epoch AI Benchmarking Hub · Codex CLI

#90 / 202
43.1%[37.2% to 49%]UnknownStandard17 Nov 2025
LMArena WebDev

LMArena · Overall · Default

#145 / 156
1,243[1,221 to 1,266]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Webdev · Default

#145 / 156
1,243[1,221 to 1,266]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Webdev HTML · Default

#145 / 155
1,252[1,229 to 1,275]UnknownStandard15 Nov 2026