in the loop

Qwen 3.5 Flash (hosted 35B-A3B)
#93 of 274 scored.

AlibabaFeb 25, 2026

Capabilities Index

Range 141.8–145.7

144.0

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond76.4%

    75th of 186

  • FrontierMath18.3%

    73rd of 81

  • SimpleQA Verified20.3%

    65th of 77

  • Mock AIME84.4%

    71st of 176

Everything else Epoch has for it

  • DTBench71.5%
  • LMCA34.3%
  • Chess Puzzles16.9%
  • Mystery Game Puzzles11.9%
  • FrontierMath-Tier-4-2025-07-01-Private0.0%

On the index

Around it.

  1. #90Grok 4 FastxAI144.2
  2. #91Gemini 2.5 Pro (Mar 2025)Google144.2
  3. #92Claude Opus 4.1Anthropic · $15 in144.1
  4. #93Qwen 3.5 Flash (hosted 35B-A3B)Alibaba144.0
  5. #94Qwen 3.6 35B-A3BAlibaba · $0.15 in143.9
  6. #95Qwen3-235B-A22B-Thinking (Jul 2025)Alibaba143.8
  7. #96GLM-4.7Z.ai · $0.60 in143.5

Sources