Acropolis

Qwen3.8 Max (0902)

AlibabaGrade B. Evidence grade B of A to D: good.ProprietaryReleased 1 Sept 2026
Compare with peers

Benchmark appearances

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

BenchmarkRankScoreCostStatusObserved
LMArena WebDev

LMArena · Image to webdev · Default

#8 / 64
1,639[1,620 to 1,658]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Webdev react · Default

#14 / 140
1,697[1,690 to 1,704]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Overall · Default

#15 / 156
1,676[1,669 to 1,682]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Webdev · Default

#15 / 156
1,676[1,669 to 1,682]UnknownStandard15 Nov 2026
LMArena WebDev

LMArena · Webdev HTML · Default

#18 / 155
1,654[1,643 to 1,665]UnknownStandard15 Nov 2026
GPQA diamond

Epoch AI Benchmarking Hub · xhigh

#36 / 338
92.3%[88.9% to 95.7%]UnknownStandard2 Sept 2026