Acropolis

Qwen3.6 35B A3B

AlibabaGrade C. Evidence grade C of A to D: thin.Open weightsReleased 16 Apr 2026
Compare with peers

Benchmark appearances

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

BenchmarkRankScoreCostStatusObserved
GPQA diamond

Epoch AI Benchmarking Hub · none

#111 / 338
84.8%[79.8% to 89.9%]UnknownStandard7 Aug 2026
GPQA diamond

Epoch AI Benchmarking Hub · Default

#118 / 338
83.8%[78.7% to 89%]UnknownStandard7 Aug 2026
Terminal Bench

Epoch AI Benchmarking Hub · little-coder

#158 / 202
24.6%[18.3% to 30.9%]UnknownStandard16 Apr 2026