Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · Qwen3.6-35B-A3B11 results · 11 benchmarks
Model card

Qwen3.6-35B-A3B.

unknown1 current SOTA
§ 02 · Benchmarks

Every benchmark Qwen3.6-35B-A3B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01RealWorldQAMultimodal · Visual Question Answeringaccuracy85.3%#1/23source ↗
02Video-MMEMultimodal · Video Understandingaccuracy86.6%#4/24source ↗
03MMMUMultimodal · Image-Text-to-Textaccuracy81.7%#6/36source ↗
04MMStarMultimodal · Image-Text-to-Textaccuracy80.7%#7/21source ↗
05MVBenchMultimodal · Video Understandingaccuracy74.6%#9/20source ↗
06LiveCodeBenchComputer Code · Code Generationpass-180.4%#10/24source ↗
07MMMU-ProMultimodal · Visual Question Answeringaccuracy75.3%#11/31source ↗
08SWE-Bench VerifiedComputer Code · Code Generationaccuracy73.4%#11/22source ↗
09GPQA DiamondReasoning · Multi-step Reasoningaccuracy86.0%#16/74source ↗
10HLEReasoning · Multi-step Reasoningaccuracy21.4%#21/36source ↗
11MMLU-ProReasoning · Commonsense Reasoningaccuracy85.2%#21/73source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where Qwen3.6-35B-A3B actually performs.

Multimodal
6
benchmarks
avg rank #6.3 · 1 SOTA
Computer Code
2
benchmarks
avg rank #10.5
Reasoning
3
benchmarks
avg rank #19.3
§ 04 · Papers

1 paper with results for Qwen3.6-35B-A3B.

  1. 2026-04-21· 11 results

    Qwen3.6

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
11
results
0 of 11 rows marked verified.