Acropolis

GPT-4 Turbo Preview (1106)

OpenAIGrade A. Evidence grade A of A to D: strongest.ProprietaryReleased 6 Nov 2023Consistent across benchmarks
Compare with peers

Domain profile

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

  • Agentic (1 boards): 14 (scale 0 to 100)Agentic (1 boards)14
  • Coding (1 boards): 14 (scale 0 to 100)Coding (1 boards)14
  • General text (2 boards): 34 (scale 0 to 100)General text (2 boards)34
  • Science (1 boards): 22 (scale 0 to 100)Science (1 boards)22

Benchmark appearances

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

BenchmarkRankScoreCostStatusObserved
METR time horizon

METR time horizons · metr_agents/react

#20 / 23Tied #1
4 min[1.9 min to 8.4 min]UnknownStandardNot stated
LMArena Text (style control)

LMArena · Polish · Default

#170 / 243
1,368[1,312 to 1,424]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Polish · Default

#187 / 243
1,326[1,271 to 1,382]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Japanese · Default

#196 / 288
1,262[1,243 to 1,281]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Japanese · Default

#209 / 288
1,210[1,191 to 1,228]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · French · Default

#221 / 301
1,340[1,318 to 1,361]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Korean · Default

#222 / 289
1,253[1,231 to 1,274]UnknownStandard11 Nov 2026
LMArena Text

LMArena · French · Default

#225 / 301
1,283[1,261 to 1,304]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · German · Default

#228 / 320
1,297[1,282 to 1,313]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Spanish · Default

#230 / 304
1,313[1,291 to 1,335]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Korean · Default

#235 / 289
1,184[1,163 to 1,206]UnknownStandard11 Nov 2026
LMArena Text

LMArena · German · Default

#238 / 320
1,250[1,235 to 1,266]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Spanish · Default

#239 / 304
1,261[1,239 to 1,283]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Math · Default

#249 / 404
1,303[1,295 to 1,311]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry entertainment and sports and media · Default

#250 / 419
1,290[1,282 to 1,298]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry writing and literature and language · Default

#253 / 420
1,307[1,301 to 1,314]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry mathematical · Default

#259 / 402
1,309[1,301 to 1,317]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Creative writing · Default

#261 / 419
1,286[1,278 to 1,294]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Russian · Default

#266 / 385
1,301[1,292 to 1,310]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Math · Default

#268 / 404
1,269[1,261 to 1,277]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Chinese · Default

#269 / 395
1,315[1,305 to 1,325]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Non English · Default

#270 / 421
1,296[1,291 to 1,302]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry entertainment and sports and media · Default

#272 / 419
1,243[1,235 to 1,250]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry mathematical · Default

#273 / 402
1,270[1,262 to 1,278]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Instruction following · Default

#273 / 421
1,296[1,291 to 1,302]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Multi turn · Default

#273 / 419
1,299[1,291 to 1,307]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry writing and literature and language · Default

#275 / 420
1,264[1,258 to 1,271]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Chinese · Default

#277 / 395
1,243[1,233 to 1,253]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Creative writing · Default

#277 / 419
1,244[1,236 to 1,252]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Overall · Default

#278 / 421
1,313[1,309 to 1,317]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Expert · Default

#280 / 371
1,291[1,279 to 1,303]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · English · Default

#282 / 421
1,325[1,320 to 1,330]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Russian · Default

#283 / 385
1,251[1,242 to 1,260]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Exclude ties · Default

#283 / 421
1,245[1,239 to 1,251]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts · Default

#283 / 421
1,313[1,307 to 1,319]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts English · Default

#284 / 419
1,325[1,318 to 1,332]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry life and physical and social science · Default

#284 / 419
1,320[1,312 to 1,327]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry medicine and healthcare · Default

#284 / 391
1,304[1,292 to 1,316]UnknownStandard11 Nov 2026
GPQA diamond

Epoch AI Benchmarking Hub · Default

#285 / 338
42.4%[37.6% to 47.1%]UnknownStandard27 Jan 2025
LMArena Text

LMArena · Non English · Default

#285 / 421
1,246[1,240 to 1,251]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry legal and government · Default

#286 / 393
1,314[1,302 to 1,325]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Expert · Default

#287 / 371
1,211[1,199 to 1,223]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Coding · Default

#287 / 416
1,340[1,333 to 1,348]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Longer query · Default

#289 / 399
1,303[1,295 to 1,311]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry medicine and healthcare · Default

#290 / 391
1,224[1,212 to 1,236]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Multi turn · Default

#290 / 419
1,257[1,249 to 1,264]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Instruction following · Default

#291 / 421
1,240[1,235 to 1,246]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Overall · Default

#291 / 421
1,263[1,260 to 1,267]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry legal and government · Default

#293 / 393
1,249[1,238 to 1,261]UnknownStandard11 Nov 2026
LMArena Text

LMArena · English · Default

#294 / 421
1,277[1,272 to 1,282]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry software and IT services · Default

#294 / 421
1,324[1,318 to 1,330]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Exclude ties · Default

#295 / 421
1,174[1,168 to 1,180]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Hard prompts English · Default

#295 / 419
1,254[1,247 to 1,261]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry life and physical and social science · Default

#295 / 419
1,255[1,247 to 1,263]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Coding · Default

#296 / 416
1,254[1,247 to 1,261]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Hard prompts · Default

#297 / 421
1,241[1,235 to 1,247]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry software and IT services · Default

#299 / 421
1,250[1,244 to 1,256]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Longer query · Default

#300 / 399
1,236[1,227 to 1,244]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry business and management and financial operations · Default

#300 / 414
1,279[1,271 to 1,288]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry business and management and financial operations · Default

#306 / 414
1,211[1,202 to 1,220]UnknownStandard11 Nov 2026

Closest head-to-head rivals

Direct pairwise win rates for GPT-4 Turbo Preview (1106) across shared benchmark boards.