Acropolis

o1-mini

OpenAIGrade B. Evidence grade B of A to D: good.ProprietaryConsistent across benchmarks
Compare with peers

Domain profile

Median within-board percentile by capability domain across boards with sufficient peer overlap.

  • General text (3 boards): 45 (scale 0 to 100)General text (3 boards)45
  • Math (1 boards): 19 (scale 0 to 100)Math (1 boards)19
  • Science (2 boards): 28 (scale 0 to 100)Science (2 boards)28

Benchmark appearances

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

BenchmarkRankScoreCostStatusObserved
FrontierMath-2025-02-28-Private

Epoch AI Benchmarking Hub · medium

#85 / 101
1.7%[0.2% to 3.2%]UnknownStandard6 Mar 2025
FrontierMath-2025-02-28-Private

Epoch AI Benchmarking Hub · high

#89 / 101
1.4%[0% to 2.7%]UnknownStandard6 Mar 2025
LMArena Text (style control)

LMArena · Japanese · Default

#190 / 288
1,277[1,258 to 1,296]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Japanese · Default

#192 / 288
1,245[1,226 to 1,264]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry mathematical · Default

#199 / 402
1,375[1,367 to 1,384]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry mathematical · Default

#203 / 402
1,366[1,358 to 1,375]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Math · Default

#210 / 404
1,361[1,353 to 1,369]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Math · Default

#211 / 404
1,358[1,350 to 1,366]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Korean · Default

#213 / 289
1,223[1,199 to 1,247]UnknownStandard11 Nov 2026
LMArena Text

LMArena · German · Default

#217 / 320
1,278[1,260 to 1,296]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Spanish · Default

#217 / 304
1,303[1,275 to 1,331]UnknownStandard11 Nov 2026
LMArena Text

LMArena · French · Default

#219 / 301
1,293[1,263 to 1,323]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Spanish · Default

#219 / 304
1,335[1,307 to 1,363]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Coding · Default

#221 / 416
1,362[1,355 to 1,370]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Korean · Default

#221 / 289
1,253[1,229 to 1,277]UnknownStandard11 Nov 2026
GPQA diamond

Epoch AI Benchmarking Hub · high

#226 / 338
62.4%[57% to 67.7%]UnknownStandard13 Feb 2025
LMArena Text (style control)

LMArena · German · Default

#226 / 320
1,301[1,283 to 1,319]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Expert · Default

#228 / 371
1,316[1,304 to 1,327]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Hard prompts English · Default

#228 / 419
1,351[1,344 to 1,359]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry software and IT services · Default

#228 / 421
1,354[1,348 to 1,360]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Expert · Default

#228 / 371
1,351[1,339 to 1,363]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Instruction following · Default

#229 / 421
1,332[1,326 to 1,337]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Hard prompts · Default

#230 / 421
1,333[1,327 to 1,339]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Longer query · Default

#231 / 399
1,320[1,313 to 1,328]UnknownStandard11 Nov 2026
GPQA diamond

Epoch AI Benchmarking Hub · medium

#232 / 338
59.5%[54% to 65%]UnknownStandard27 Jan 2025
LMArena Text (style control)

LMArena · Hard prompts · Default

#232 / 421
1,360[1,354 to 1,366]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Coding · Default

#233 / 416
1,386[1,378 to 1,393]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts English · Default

#233 / 419
1,373[1,365 to 1,380]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Longer query · Default

#234 / 399
1,344[1,337 to 1,352]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · French · Default

#235 / 301
1,324[1,295 to 1,354]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Instruction following · Default

#236 / 421
1,304[1,299 to 1,309]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry software and IT services · Default

#236 / 421
1,374[1,368 to 1,381]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry legal and government · Default

#239 / 393
1,315[1,304 to 1,327]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Multi turn · Default

#239 / 419
1,314[1,307 to 1,321]UnknownStandard11 Nov 2026
LMArena Text

LMArena · English · Default

#240 / 421
1,340[1,335 to 1,345]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry legal and government · Default

#240 / 393
1,343[1,331 to 1,355]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Chinese · Default

#241 / 395
1,350[1,340 to 1,360]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Exclude ties · Default

#241 / 421
1,291[1,285 to 1,296]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Non English · Default

#242 / 421
1,315[1,310 to 1,320]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Overall · Default

#242 / 421
1,337[1,333 to 1,341]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Chinese · Default

#243 / 395
1,314[1,304 to 1,324]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Exclude ties · Default

#243 / 421
1,263[1,257 to 1,268]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Overall · Default

#243 / 421
1,317[1,313 to 1,321]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Non English · Default

#244 / 421
1,289[1,284 to 1,293]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · English · Default

#246 / 421
1,353[1,348 to 1,358]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry writing and literature and language · Default

#246 / 420
1,311[1,305 to 1,317]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry life and physical and social science · Default

#248 / 419
1,316[1,309 to 1,323]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry business and management and financial operations · Default

#249 / 414
1,287[1,278 to 1,295]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry medicine and healthcare · Default

#250 / 391
1,297[1,284 to 1,309]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Russian · Default

#250 / 385
1,282[1,274 to 1,290]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Multi turn · Default

#250 / 419
1,323[1,315 to 1,330]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Russian · Default

#252 / 385
1,310[1,303 to 1,318]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry business and management and financial operations · Default

#254 / 414
1,318[1,310 to 1,327]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry medicine and healthcare · Default

#254 / 391
1,338[1,325 to 1,350]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry life and physical and social science · Default

#258 / 419
1,340[1,333 to 1,348]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry entertainment and sports and media · Default

#259 / 419
1,257[1,250 to 1,264]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry writing and literature and language · Default

#259 / 420
1,280[1,274 to 1,286]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry entertainment and sports and media · Default

#265 / 419
1,282[1,274 to 1,289]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Creative writing · Default

#268 / 419
1,281[1,273 to 1,289]UnknownStandard11 Nov 2026
ARC-AGI-2

Epoch AI Benchmarking Hub · Default

#271 / 299
0.8%$0.19StandardNot stated
LMArena Text

LMArena · Creative writing · Default

#278 / 419
1,244[1,236 to 1,252]UnknownStandard11 Nov 2026

Reasoning effort scaling

Same benchmark and harness measured across multiple reasoning effort settings.

  • FrontierMath-2025-02-28-Private

    Epoch AI Benchmarking Hub

    1 regression. Evidence grade D of A to D: weakest.
    medium

    1.7

    high

    1.4

  • GPQA diamond

    Epoch AI Benchmarking Hub

    Monotone. Evidence grade A of A to D: strongest.
    medium

    59.5

    high

    62.4

Closest head-to-head rivals

Direct pairwise win rates for o1-mini across shared benchmark boards.