Qwen3.6 35B A3B — Benchmarks

Benchmark scores for Qwen3.6 35B A3B aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #47 of 78 open modelscomposite 40.8/100 across 10 benchmarks in 3 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode35.8%#38 / 62#132 / 161
WeirdML34.5%#35 / 46#132 / 161
Terminal-Bench23.0%#13 / 16#50 / 57
Surface Evolver Bench44.4%#8 / 13#21 / 27

Math

BenchmarkScoreOpen rankAll models
FrontierMath20.3%#15 / 15#73 / 102
AIME 2024/202586.7%#18 / 82#78 / 270

Reasoning

BenchmarkScoreOpen rankAll models
Chess Puzzles26.0%#5 / 65#62 / 205
Mystery Game Puzzles22.0%#5 / 17#47 / 122
DTBench73.9%#30 / 67#130 / 210
LMCA29.7%#19 / 53#112 / 172
GPQA Diamond84.9%#19 / 94#84 / 289
CritPt0.3%#42 / 62#134 / 172

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.