Acropolis

GPT-4.1 nano

OpenAIGrade B. Evidence grade B of A to D: good.ProprietaryReleased 14 Apr 2025Consistent across benchmarks
Compare with peers

Domain profile

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

  • General text (3 boards): 38 (scale 0 to 100)General text (3 boards)38
  • Math (1 boards): 14 (scale 0 to 100)Math (1 boards)14
  • Science (2 boards): 17 (scale 0 to 100)Science (2 boards)17
  • Vision (2 boards): 18 (scale 0 to 100)Vision (2 boards)18

Benchmark appearances

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

BenchmarkRankScoreCostStatusObserved
FrontierMath-2025-02-28-Private

Epoch AI Benchmarking Hub · Default

#90 / 101
1%[0.3% to 3.2%]UnknownStandard14 Apr 2025
LMArena Vision (style control)

LMArena · English · Default

#131 / 167
1,124[1,097 to 1,150]UnknownStandard9 Nov 2026
LMArena Vision

LMArena · English · Default

#132 / 167
1,101[1,074 to 1,127]UnknownStandard9 Nov 2026
LMArena Vision

LMArena · Overall · Default

#139 / 167
1,063[1,045 to 1,081]UnknownStandard9 Nov 2026
LMArena Vision (style control)

LMArena · Overall · Default

#139 / 167
1,089[1,070 to 1,107]UnknownStandard9 Nov 2026
LMArena Text (style control)

LMArena · German · Default

#205 / 320
1,322[1,285 to 1,359]UnknownStandard11 Nov 2026
LMArena Text

LMArena · German · Default

#209 / 320
1,288[1,251 to 1,324]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Japanese · Default

#217 / 288
1,233[1,188 to 1,279]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Japanese · Default

#219 / 288
1,199[1,154 to 1,244]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Creative writing · Default

#232 / 419
1,307[1,289 to 1,325]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry legal and government · Default

#232 / 393
1,352[1,323 to 1,380]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Coding · Default

#245 / 416
1,373[1,354 to 1,392]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry software and IT services · Default

#246 / 421
1,362[1,347 to 1,376]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry life and physical and social science · Default

#247 / 419
1,349[1,333 to 1,366]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Expert · Default

#248 / 371
1,271[1,241 to 1,301]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry medicine and healthcare · Default

#248 / 391
1,342[1,310 to 1,374]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry business and management and financial operations · Default

#250 / 414
1,321[1,299 to 1,343]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Expert · Default

#255 / 371
1,313[1,282 to 1,344]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts · Default

#255 / 421
1,333[1,319 to 1,346]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry entertainment and sports and media · Default

#255 / 419
1,287[1,270 to 1,304]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry legal and government · Default

#257 / 393
1,300[1,272 to 1,328]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Math · Default

#259 / 404
1,274[1,251 to 1,297]UnknownStandard11 Nov 2026
GPQA diamond

Epoch AI Benchmarking Hub · Default

#260 / 338
48.9%[44.1% to 53.8%]UnknownStandard14 Apr 2025
LMArena Text

LMArena · Hard prompts · Default

#260 / 421
1,286[1,272 to 1,299]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry software and IT services · Default

#260 / 421
1,305[1,290 to 1,319]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Coding · Default

#261 / 416
1,306[1,286 to 1,325]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry business and management and financial operations · Default

#261 / 414
1,266[1,245 to 1,288]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry life and physical and social science · Default

#261 / 419
1,297[1,281 to 1,314]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Multi turn · Default

#261 / 419
1,314[1,296 to 1,332]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Overall · Default

#261 / 421
1,322[1,315 to 1,330]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry medicine and healthcare · Default

#262 / 391
1,276[1,244 to 1,309]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Hard prompts English · Default

#263 / 419
1,293[1,276 to 1,309]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Exclude ties · Default

#263 / 421
1,267[1,254 to 1,279]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts English · Default

#263 / 419
1,338[1,321 to 1,355]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Chinese · Default

#264 / 395
1,270[1,234 to 1,306]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · English · Default

#264 / 421
1,340[1,330 to 1,350]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Creative writing · Default

#265 / 419
1,260[1,242 to 1,278]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Instruction following · Default

#265 / 421
1,266[1,254 to 1,279]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Chinese · Default

#265 / 395
1,321[1,285 to 1,357]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry writing and literature and language · Default

#266 / 420
1,299[1,285 to 1,314]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Longer query · Default

#266 / 399
1,325[1,305 to 1,345]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry mathematical · Default

#267 / 402
1,275[1,251 to 1,299]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Non English · Default

#267 / 421
1,298[1,287 to 1,309]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Russian · Default

#267 / 385
1,300[1,280 to 1,321]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Longer query · Default

#268 / 399
1,283[1,263 to 1,302]UnknownStandard11 Nov 2026
LMArena Text

LMArena · English · Default

#269 / 421
1,303[1,293 to 1,313]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Overall · Default

#269 / 421
1,285[1,277 to 1,292]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Instruction following · Default

#269 / 421
1,300[1,288 to 1,313]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Multi turn · Default

#270 / 419
1,277[1,259 to 1,295]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry entertainment and sports and media · Default

#271 / 419
1,243[1,225 to 1,260]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Russian · Default

#271 / 385
1,261[1,240 to 1,282]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Exclude ties · Default

#272 / 421
1,210[1,198 to 1,222]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Non English · Default

#273 / 421
1,260[1,249 to 1,271]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry writing and literature and language · Default

#277 / 420
1,261[1,247 to 1,275]UnknownStandard11 Nov 2026
ARC-AGI-2

Epoch AI Benchmarking Hub · Default

#281 / 299
0%$0.00StandardNot stated
LMArena Text (style control)

LMArena · Math · Default

#282 / 404
1,273[1,250 to 1,296]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry mathematical · Default

#283 / 402
1,279[1,255 to 1,303]UnknownStandard11 Nov 2026

Closest head-to-head rivals

Direct pairwise win rates for GPT-4.1 nano across shared benchmark boards.