Acropolis

Kimi K2 Thinking Turbo

Moonshot AIGrade B. Evidence grade B of A to D: good.Open weightsReleased 6 Nov 2025Consistent across benchmarks
Compare with peers

Domain profile

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

  • Coding (1 boards): 15 (scale 0 to 100)Coding (1 boards)15
  • General text (2 boards): 72 (scale 0 to 100)General text (2 boards)72
  • Science (1 boards): 64 (scale 0 to 100)Science (1 boards)64

Benchmark appearances

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

BenchmarkRankScoreCostStatusObserved
LMArena Text

LMArena · Coding · Default

#97 / 416
1,454[1,448 to 1,459]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry mathematical · Default

#101 / 402
1,437[1,426 to 1,448]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Math · Default

#102 / 404
1,435[1,426 to 1,445]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry mathematical · Default

#103 / 402
1,444[1,434 to 1,455]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Expert · Default

#105 / 371
1,439[1,430 to 1,448]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Coding · Default

#105 / 416
1,486[1,481 to 1,492]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Math · Default

#106 / 404
1,428[1,419 to 1,438]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Chinese · Default

#107 / 395
1,473[1,464 to 1,482]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry software and IT services · Default

#107 / 421
1,473[1,469 to 1,478]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Expert · Default

#108 / 371
1,461[1,452 to 1,470]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · English · Default

#111 / 421
1,443[1,438 to 1,447]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry software and IT services · Default

#112 / 421
1,446[1,442 to 1,451]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Polish · Default

#112 / 243
1,420[1,406 to 1,435]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts · Default

#114 / 421
1,453[1,449 to 1,457]UnknownStandard11 Nov 2026
GPQA diamond

Epoch AI Benchmarking Hub · Default

#117 / 338
84.2%[80.1% to 88.3%]UnknownStandard11 Nov 2025
LMArena Text (style control)

LMArena · Exclude ties · Default

#117 / 421
1,423[1,419 to 1,427]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Instruction following · Default

#117 / 421
1,418[1,413 to 1,423]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Non English · Default

#117 / 421
1,412[1,408 to 1,416]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Hard prompts · Default

#118 / 421
1,428[1,424 to 1,432]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Longer query · Default

#118 / 399
1,415[1,410 to 1,420]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · French · Default

#118 / 301
1,445[1,429 to 1,461]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Multi turn · Default

#118 / 419
1,432[1,426 to 1,438]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Overall · Default

#118 / 421
1,430[1,427 to 1,433]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts English · Default

#119 / 419
1,458[1,452 to 1,463]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Chinese · Default

#120 / 395
1,456[1,447 to 1,465]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Hard prompts English · Default

#122 / 419
1,433[1,428 to 1,438]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry entertainment and sports and media · Default

#123 / 419
1,395[1,389 to 1,401]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Japanese · Default

#123 / 288
1,370[1,345 to 1,395]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry legal and government · Default

#124 / 393
1,435[1,426 to 1,444]UnknownStandard11 Nov 2026
LMArena Text

LMArena · French · Default

#125 / 301
1,426[1,410 to 1,442]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Longer query · Default

#125 / 399
1,434[1,429 to 1,439]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Japanese · Default

#126 / 288
1,358[1,333 to 1,384]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Creative writing · Default

#126 / 419
1,391[1,385 to 1,398]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry medicine and healthcare · Default

#126 / 391
1,445[1,435 to 1,454]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Spanish · Default

#126 / 304
1,416[1,402 to 1,430]UnknownStandard11 Nov 2026
LMArena WebDev

LMArena · Webdev react · Default

#126 / 140
1,313[1,303 to 1,323]UnknownStandard15 Nov 2026
LMArena Text

LMArena · Instruction following · Default

#127 / 421
1,403[1,398 to 1,408]UnknownStandard11 Nov 2026
LMArena Text

LMArena · English · Default

#128 / 421
1,426[1,422 to 1,431]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · German · Default

#129 / 320
1,411[1,393 to 1,429]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry business and management and financial operations · Default

#130 / 414
1,421[1,415 to 1,427]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry life and physical and social science · Default

#130 / 419
1,441[1,435 to 1,448]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Multi turn · Default

#132 / 419
1,414[1,408 to 1,420]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry writing and literature and language · Default

#132 / 420
1,399[1,393 to 1,404]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Russian · Default

#132 / 385
1,411[1,404 to 1,418]UnknownStandard11 Nov 2026
LMArena WebDev

LMArena · Webdev HTML · Default

#132 / 155
1,325[1,314 to 1,336]UnknownStandard15 Nov 2026
LMArena Text

LMArena · Industry medicine and healthcare · Default

#134 / 391
1,417[1,407 to 1,426]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Polish · Default

#134 / 243
1,396[1,382 to 1,410]UnknownStandard11 Nov 2026
LMArena WebDev

LMArena · Overall · Default

#134 / 156
1,322[1,314 to 1,329]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Webdev · Default

#134 / 156
1,322[1,314 to 1,329]UnknownStandard15 Nov 2026
LMArena Text

LMArena · Exclude ties · Default

#135 / 421
1,400[1,396 to 1,404]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry entertainment and sports and media · Default

#135 / 419
1,378[1,372 to 1,383]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Overall · Default

#135 / 421
1,414[1,411 to 1,417]UnknownStandard11 Nov 2026
LMArena Text

LMArena · German · Default

#137 / 320
1,390[1,372 to 1,408]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Spanish · Default

#137 / 304
1,407[1,393 to 1,421]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Non English · Default

#140 / 421
1,397[1,394 to 1,401]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Creative writing · Default

#142 / 419
1,374[1,367 to 1,380]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry legal and government · Default

#143 / 393
1,416[1,407 to 1,425]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry life and physical and social science · Default

#147 / 419
1,419[1,413 to 1,425]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry business and management and financial operations · Default

#149 / 414
1,397[1,392 to 1,403]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry writing and literature and language · Default

#150 / 420
1,381[1,375 to 1,386]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Russian · Default

#151 / 385
1,390[1,383 to 1,397]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Korean · Default

#156 / 289
1,342[1,323 to 1,362]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Korean · Default

#157 / 289
1,329[1,310 to 1,349]UnknownStandard11 Nov 2026

Closest head-to-head rivals

Direct pairwise win rates for Kimi K2 Thinking Turbo across shared benchmark boards.