in the loop

Qwen 3.5 Plus (hosted 397B-A17B)
#71 of 274 scored.

AlibabaFeb 16, 2026

Capabilities Index

Range 144.7–147.9

146.8

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond79.8%

    65th of 186

  • SimpleQA Verified25.4%

    63rd of 77

  • Mock AIME86.7%

    61st of 176

Everything else Epoch has for it

  • DTBench67.5%
  • LMCA42.8%
  • FrontierMath-2025-02-28-Private36.9%
  • CL-bench19.8%
  • Chess Puzzles17.9%
  • CL-bench Life12.4%
  • Mystery Game Puzzles8.6%
  • FrontierMath-Tier-4-2025-07-01-Private3.5%

On the index

Around it.

  1. #68MiniMax-M3MiniMax · $0.30 in146.9
  2. #69o3OpenAI · $2.00 in146.9
  3. #70Claude Sonnet 4.5Anthropic · $3.00 in146.8
  4. #71Qwen 3.5 Plus (hosted 397B-A17B)Alibaba146.8
  5. #72MiniMax-M2.5MiniMax · $0.27 in146.7
  6. #73Qwen3.5 397B-A17BAlibaba · $0.55 in146.7
  7. #74Qwen3.6 27BAlibaba · $0.32 in146.5

Sources