Acropolis

o1

OpenAIGrade A. Evidence grade A of A to D: strongest.ProprietaryReleased 5 Dec 2024Consistent across benchmarks
Compare with peers

Domain profile

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

  • Agentic (1 boards): 36 (scale 0 to 100)Agentic (1 boards)36
  • Coding (1 boards): 36 (scale 0 to 100)Coding (1 boards)36
  • General text (3 boards): 56 (scale 0 to 100)General text (3 boards)56
  • Math (2 boards): 35 (scale 0 to 100)Math (2 boards)35
  • Science (2 boards): 39 (scale 0 to 100)Science (2 boards)39
  • Vision (2 boards): 40 (scale 0 to 100)Vision (2 boards)40

Benchmark appearances

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

BenchmarkRankScoreCostStatusObserved
METR time horizon

METR time horizons · triframe_inspect/triframe_agent

#15 / 23Tied #1
38.8 min[21.2 min to 65 min]UnknownStandardNot stated
HLE

Epoch AI Benchmarking Hub · Default

#40 / 56
8%[5.9% to 10%]UnknownStandardNot stated
FrontierMath-2025-02-28-Private

Epoch AI Benchmarking Hub · high

#57 / 101
9.3%[6% to 12.7%]UnknownStandard7 Mar 2025
LMArena Vision (style control)

LMArena · Chinese · Default

#74 / 135
1,264[1,208 to 1,321]UnknownStandard9 Nov 2026
LMArena Text

LMArena · Korean · Default

#76 / 289
1,396[1,365 to 1,428]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Korean · Default

#76 / 289
1,410[1,378 to 1,442]UnknownStandard11 Nov 2026
LMArena Vision

LMArena · Chinese · Default

#86 / 135
1,235[1,176 to 1,293]UnknownStandard9 Nov 2026
LMArena Vision (style control)

LMArena · Overall · Default

#97 / 167
1,193[1,182 to 1,204]UnknownStandard9 Nov 2026
LMArena Vision (style control)

LMArena · English · Default

#103 / 167
1,186[1,172 to 1,201]UnknownStandard9 Nov 2026
LMArena Vision

LMArena · Overall · Default

#111 / 167
1,168[1,157 to 1,179]UnknownStandard9 Nov 2026
LMArena Vision

LMArena · English · Default

#116 / 167
1,162[1,148 to 1,177]UnknownStandard9 Nov 2026
LMArena Text (style control)

LMArena · Japanese · Default

#118 / 288
1,374[1,348 to 1,400]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry entertainment and sports and media · Default

#127 / 419
1,390[1,381 to 1,398]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry writing and literature and language · Default

#134 / 420
1,398[1,391 to 1,405]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Japanese · Default

#135 / 288
1,346[1,320 to 1,372]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Instruction following · Default

#141 / 421
1,407[1,400 to 1,414]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Creative writing · Default

#147 / 419
1,381[1,372 to 1,390]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Math · Default

#151 / 404
1,409[1,398 to 1,420]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry mathematical · Default

#152 / 402
1,414[1,403 to 1,426]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Longer query · Default

#158 / 399
1,412[1,403 to 1,422]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry entertainment and sports and media · Default

#162 / 419
1,358[1,349 to 1,367]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry legal and government · Default

#162 / 393
1,407[1,391 to 1,422]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Non English · Default

#162 / 421
1,390[1,384 to 1,396]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Exclude ties · Default

#163 / 421
1,386[1,380 to 1,393]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Overall · Default

#163 / 421
1,402[1,398 to 1,407]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Chinese · Default

#164 / 395
1,429[1,415 to 1,444]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Spanish · Default

#164 / 304
1,392[1,344 to 1,441]UnknownStandard11 Nov 2026
GPQA diamond

Epoch AI Benchmarking Hub · high

#165 / 338
76.8%[70.9% to 82.7%]UnknownStandard13 Feb 2025
LMArena Text (style control)

LMArena · German · Default

#166 / 320
1,375[1,351 to 1,399]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Russian · Default

#170 / 385
1,387[1,377 to 1,398]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Creative writing · Default

#171 / 419
1,347[1,338 to 1,356]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts · Default

#171 / 421
1,418[1,410 to 1,426]UnknownStandard11 Nov 2026
GPQA diamond

Epoch AI Benchmarking Hub · medium

#172 / 338
75.8%[69.8% to 81.7%]UnknownStandard27 Jan 2025
LMArena Text (style control)

LMArena · English · Default

#172 / 421
1,412[1,406 to 1,417]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Instruction following · Default

#175 / 421
1,367[1,361 to 1,374]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry life and physical and social science · Default

#175 / 419
1,411[1,402 to 1,420]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry writing and literature and language · Default

#176 / 420
1,360[1,353 to 1,367]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry mathematical · Default

#178 / 402
1,390[1,378 to 1,401]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts English · Default

#179 / 419
1,422[1,413 to 1,432]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Longer query · Default

#180 / 399
1,378[1,368 to 1,387]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Math · Default

#180 / 404
1,388[1,378 to 1,399]UnknownStandard11 Nov 2026
GPQA diamond

Epoch AI Benchmarking Hub · low

#183 / 338
74.2%[68.1% to 80.3%]UnknownStandard20 Jul 2026
LMArena Text (style control)

LMArena · Expert · Default

#183 / 371
1,402[1,385 to 1,419]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry software and IT services · Default

#184 / 421
1,422[1,415 to 1,430]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Chinese · Default

#186 / 395
1,394[1,380 to 1,408]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Non English · Default

#186 / 421
1,358[1,352 to 1,365]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Coding · Default

#186 / 416
1,433[1,423 to 1,442]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · French · Default

#186 / 301
1,386[1,349 to 1,423]UnknownStandard11 Nov 2026
LMArena Text

LMArena · German · Default

#187 / 320
1,337[1,312 to 1,361]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Russian · Default

#189 / 385
1,356[1,345 to 1,366]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry medicine and healthcare · Default

#189 / 391
1,400[1,382 to 1,417]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Multi turn · Default

#190 / 419
1,386[1,377 to 1,395]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Hard prompts · Default

#192 / 421
1,371[1,364 to 1,379]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Expert · Default

#193 / 371
1,361[1,344 to 1,378]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry legal and government · Default

#193 / 393
1,368[1,353 to 1,384]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Exclude ties · Default

#194 / 421
1,334[1,327 to 1,340]UnknownStandard11 Nov 2026
LMArena Text

LMArena · French · Default

#196 / 301
1,344[1,307 to 1,381]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Overall · Default

#196 / 421
1,366[1,361 to 1,370]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry business and management and financial operations · Default

#197 / 414
1,370[1,358 to 1,382]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry life and physical and social science · Default

#202 / 419
1,369[1,360 to 1,378]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Multi turn · Default

#202 / 419
1,355[1,346 to 1,364]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Spanish · Default

#202 / 304
1,345[1,297 to 1,393]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry medicine and healthcare · Default

#208 / 391
1,355[1,338 to 1,372]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Hard prompts English · Default

#209 / 419
1,372[1,363 to 1,381]UnknownStandard11 Nov 2026
LMArena Text

LMArena · English · Default

#210 / 421
1,372[1,367 to 1,378]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry software and IT services · Default

#213 / 421
1,366[1,359 to 1,374]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Coding · Default

#214 / 416
1,367[1,357 to 1,376]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry business and management and financial operations · Default

#217 / 414
1,327[1,316 to 1,339]UnknownStandard11 Nov 2026

Reasoning effort scaling

Same benchmark and harness measured across multiple reasoning effort settings.

  • GPQA diamond

    Epoch AI Benchmarking Hub

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

    74.2

    medium

    75.8

    high

    76.8

Closest head-to-head rivals

Direct pairwise win rates for o1 across shared benchmark boards.