Acropolis

Qwen3.8-27B

AlibabaGrade A. Evidence grade A of A to D: strongest.Open weightsReleased 14 Aug 2026Consistent across benchmarks
Compare with peers

Domain profile

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

  • Agentic (2 boards): 21 (scale 0 to 100)Agentic (2 boards)21
  • Coding (3 boards): 28 (scale 0 to 100)Coding (3 boards)28
  • General text (3 boards): 76 (scale 0 to 100)General text (3 boards)76
  • Science (1 boards): 55 (scale 0 to 100)Science (1 boards)55
  • Vision (2 boards): 72 (scale 0 to 100)Vision (2 boards)72

Benchmark appearances

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

BenchmarkRankScoreCostStatusObserved
LMArena WebDev

LMArena · Image to webdev · Default

#25 / 64
1,574[1,567 to 1,582]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Overall · Default

#40 / 156
1,590[1,584 to 1,596]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Webdev · Default

#40 / 156
1,590[1,584 to 1,596]UnknownStandard15 Nov 2026
LMArena Vision

LMArena · Chinese · Default

#41 / 135
1,327[1,300 to 1,353]UnknownStandard9 Nov 2026
LMArena WebDev

LMArena · Webdev HTML · Default

#41 / 155
1,570[1,558 to 1,582]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Webdev react · Default

#41 / 140
1,596[1,589 to 1,603]UnknownStandard15 Nov 2026
LMArena Vision

LMArena · OCR · Default

#42 / 123
1,280[1,272 to 1,288]UnknownStandard9 Nov 2026
LMArena Vision

LMArena · Overall · Default

#42 / 167
1,270[1,262 to 1,277]UnknownStandard9 Nov 2026
LMArena Vision

LMArena · English · Default

#46 / 167
1,272[1,261 to 1,284]UnknownStandard9 Nov 2026
LMArena Agent

LMArena · Overall · Default

#47 / 64
-0.1[-0.1 to -0]$0.39Standard15 Nov 2026
LMArena Vision

LMArena · Diagram · Default

#49 / 123
1,281[1,268 to 1,293]UnknownStandard9 Nov 2026
LMArena Vision

LMArena · Homework · Default

#51 / 118
1,284[1,267 to 1,301]UnknownStandard9 Nov 2026
LMArena Text

LMArena · Expert · Default

#54 / 371
1,479[1,468 to 1,489]UnknownStandard11 Nov 2026
LMArena Vision (style control)

LMArena · Chinese · Default

#54 / 135
1,293[1,267 to 1,320]UnknownStandard9 Nov 2026
LMArena Text

LMArena · French · Default

#55 / 301
1,466[1,447 to 1,484]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry life and physical and social science · Default

#55 / 419
1,463[1,455 to 1,472]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry software and IT services · Default

#56 / 421
1,474[1,468 to 1,481]UnknownStandard11 Nov 2026
LMArena Vision

LMArena · Humor · Default

#56 / 102
1,245[1,217 to 1,273]UnknownStandard9 Nov 2026
LMArena Vision (style control)

LMArena · OCR · Default

#57 / 123
1,261[1,253 to 1,269]UnknownStandard9 Nov 2026
LMArena Vision (style control)

LMArena · Homework · Default

#58 / 118
1,274[1,257 to 1,292]UnknownStandard9 Nov 2026
LMArena Text

LMArena · Coding · Default

#59 / 416
1,479[1,472 to 1,486]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry business and management and financial operations · Default

#60 / 414
1,440[1,431 to 1,448]UnknownStandard11 Nov 2026
LMArena Vision (style control)

LMArena · Overall · Default

#61 / 167
1,243[1,235 to 1,251]UnknownStandard9 Nov 2026
LMArena Vision (style control)

LMArena · English · Default

#62 / 167
1,242[1,230 to 1,254]UnknownStandard9 Nov 2026
LMArena Text

LMArena · Hard prompts English · Default

#64 / 419
1,462[1,455 to 1,469]UnknownStandard11 Nov 2026
LMArena Vision (style control)

LMArena · Diagram · Default

#64 / 123
1,267[1,254 to 1,279]UnknownStandard9 Nov 2026
LMArena Text

LMArena · Hard prompts · Default

#66 / 421
1,456[1,451 to 1,461]UnknownStandard11 Nov 2026
LMArena Vision

LMArena · Creative writing vision · Default

#66 / 106
1,234[1,212 to 1,255]UnknownStandard9 Nov 2026
LMArena Vision (style control)

LMArena · Humor · Default

#66 / 102
1,217[1,189 to 1,245]UnknownStandard9 Nov 2026
LMArena Text

LMArena · Chinese · Default

#67 / 395
1,493[1,481 to 1,506]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Polish · Default

#67 / 243
1,441[1,415 to 1,467]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry mathematical · Default

#68 / 402
1,461[1,447 to 1,475]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Math · Default

#68 / 404
1,455[1,440 to 1,470]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Longer query · Default

#69 / 399
1,446[1,440 to 1,453]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Instruction following · Default

#73 / 421
1,431[1,425 to 1,438]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Math · Default

#76 / 404
1,451[1,436 to 1,466]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry legal and government · Default

#78 / 393
1,446[1,433 to 1,458]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Spanish · Default

#79 / 304
1,443[1,424 to 1,461]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry mathematical · Default

#79 / 402
1,456[1,442 to 1,470]UnknownStandard11 Nov 2026
LMArena Text

LMArena · English · Default

#81 / 421
1,447[1,441 to 1,453]UnknownStandard11 Nov 2026
LMArena Text

LMArena · German · Default

#82 / 320
1,436[1,410 to 1,463]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Japanese · Default

#82 / 288
1,398[1,371 to 1,424]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Chinese · Default

#84 / 395
1,487[1,475 to 1,500]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · French · Default

#84 / 301
1,467[1,448 to 1,486]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Overall · Default

#85 / 421
1,437[1,432 to 1,441]UnknownStandard11 Nov 2026
LMArena Vision (style control)

LMArena · Creative writing vision · Default

#85 / 106
1,193[1,172 to 1,215]UnknownStandard9 Nov 2026
LMArena Text

LMArena · Non English · Default

#88 / 421
1,424[1,418 to 1,429]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry software and IT services · Default

#88 / 421
1,484[1,478 to 1,491]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Exclude ties · Default

#89 / 421
1,429[1,423 to 1,435]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Korean · Default

#89 / 289
1,389[1,362 to 1,415]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Coding · Default

#89 / 416
1,496[1,489 to 1,503]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry life and physical and social science · Default

#90 / 419
1,462[1,453 to 1,471]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Japanese · Default

#90 / 288
1,407[1,381 to 1,434]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Expert · Default

#92 / 371
1,473[1,462 to 1,483]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Multi turn · Default

#95 / 419
1,436[1,427 to 1,445]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Polish · Default

#96 / 243
1,441[1,415 to 1,467]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry medicine and healthcare · Default

#101 / 391
1,439[1,425 to 1,452]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Korean · Default

#101 / 289
1,387[1,360 to 1,414]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · German · Default

#103 / 320
1,434[1,407 to 1,461]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts · Default

#106 / 421
1,458[1,453 to 1,464]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry business and management and financial operations · Default

#106 / 414
1,440[1,432 to 1,449]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Non English · Default

#107 / 421
1,422[1,417 to 1,428]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Longer query · Default

#109 / 399
1,443[1,436 to 1,449]UnknownStandard11 Nov 2026
Bug Hunt Bench

Bug Hunt Bench · xhigh · Claude Code

#110 / 145
15$5.55Standard15 Sept 2026
LMArena Text (style control)

LMArena · Overall · Default

#111 / 421
1,434[1,429 to 1,438]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Exclude ties · Default

#112 / 421
1,428[1,422 to 1,434]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Multi turn · Default

#112 / 419
1,436[1,427 to 1,445]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Spanish · Default

#112 / 304
1,428[1,409 to 1,446]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry writing and literature and language · Default

#114 / 420
1,401[1,393 to 1,408]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Hard prompts English · Default

#114 / 419
1,460[1,452 to 1,467]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · English · Default

#116 / 421
1,441[1,434 to 1,447]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Instruction following · Default

#116 / 421
1,419[1,412 to 1,425]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Industry entertainment and sports and media · Default

#121 / 419
1,388[1,380 to 1,395]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry legal and government · Default

#122 / 393
1,437[1,425 to 1,450]UnknownStandard11 Nov 2026
LMArena Text

LMArena · Russian · Default

#123 / 385
1,408[1,398 to 1,417]UnknownStandard11 Nov 2026
Bug Hunt Bench

Bug Hunt Bench · Claude Code · 8-bit

#125 / 145
10.7$2.97Standard16 Sept 2026
LMArena Text (style control)

LMArena · Russian · Default

#131 / 385
1,411[1,402 to 1,421]UnknownStandard11 Nov 2026
ARC-AGI-2

Epoch AI Benchmarking Hub · xhigh

#135 / 299
42.4%UnknownStandardNot stated
LMArena Text

LMArena · Creative writing · Default

#136 / 419
1,377[1,368 to 1,385]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry medicine and healthcare · Default

#136 / 391
1,440[1,426 to 1,453]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry writing and literature and language · Default

#145 / 420
1,391[1,384 to 1,399]UnknownStandard11 Nov 2026
LMArena Text (style control)

LMArena · Industry entertainment and sports and media · Default

#150 / 419
1,376[1,369 to 1,384]UnknownStandard11 Nov 2026
ARC-AGI-2

Epoch AI Benchmarking Hub · low

#162 / 299
22.8%UnknownStandardNot stated
LMArena Text (style control)

LMArena · Creative writing · Default

#172 / 419
1,359[1,351 to 1,367]UnknownStandard11 Nov 2026
ARC-AGI-2

Epoch AI Benchmarking Hub · medium

#176 / 299
13.2%UnknownStandardNot stated
ARC-AGI-2

Epoch AI Benchmarking Hub · none

#252 / 299
1.5%UnknownStandardNot stated

Reasoning effort scaling

Same benchmark and harness measured across multiple reasoning effort settings.

  • ARC-AGI-2

    Epoch AI Benchmarking Hub

    1 regression. Evidence grade D of A to D: weakest.
    none

    1.5

    low

    22.8

    medium

    13.2

    xhigh

    42.4

Closest head-to-head rivals

Direct pairwise win rates for Qwen3.8-27B across shared benchmark boards.