Acropolis

Qwen3.5 Plus

AlibabaGrade C. Evidence grade C of A to D: thin.ProprietaryReleased 16 Feb 2026Consistent across benchmarks
Compare with peers

Domain profile

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

  • Agentic (1 boards): 6 (scale 0 to 100)Agentic (1 boards)6
  • Finance (1 boards): 6 (scale 0 to 100)Finance (1 boards)6
  • Math (1 boards): 60 (scale 0 to 100)Math (1 boards)60
  • 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
FrontierMath-2025-02-28-Private

Epoch AI Benchmarking Hub · Default

#38 / 101
21%[16.3% to 25.7%]UnknownStandard14 May 2026
Vending-Bench 2

Epoch AI Benchmarking Hub · Default

#68 / 72
$0.54UnknownStandardNot stated
GPQA diamond

Epoch AI Benchmarking Hub · Default

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

Closest head-to-head rivals

Direct pairwise win rates for Qwen3.5 Plus across shared benchmark boards.