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-VL-235B-A22B-ThinkingQwen14 results · 13 benchmarks
Model card

Qwen3-VL-235B-A22B-Thinking.

QwenLarge language model

Added from Papers with Code MMLU-Pro refresh on 2026-05-19.

§ 02 · Benchmarks

Every benchmark Qwen3-VL-235B-A22B-Thinking has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01DocVQAComputer Vision · Document Understandinganls96.5%#2/21source ↗
02MMBenchMultimodal · Visual Question Answeringaccuracy88.8%#6/20source ↗
03MVBenchMultimodal · Video Understandingaccuracy75.2%#6/20source ↗
04MMMUMultimodal · Image-Text-to-Textaccuracy80.6%#8/36source ↗
05RealWorldQAMultimodal · Visual Question Answeringaccuracy81.3%#8/23source ↗
06AIME 2025Reasoning · Mathematical Reasoningaccuracy89.7%#9/22source ↗
07MMStarMultimodal · Image-Text-to-Textaccuracy78.7%#9/21source ↗
08Video-MMEMultimodal · Video Understandingaccuracy79.0%#9/24source ↗
09OSWorldAgentic AI · Web & Desktop Agentssuccess-rate38.1%#10/28source ↗
10LiveCodeBenchComputer Code · Code Generationpass-170.1%#17/24source ↗
11MMMU-ProMultimodal · Visual Question Answeringaccuracy69.3%#18/31source ↗
12GPQA DiamondReasoning · Multi-step Reasoningaccuracy77.1%#35/74source ↗
13MMLU-ProReasoning · Commonsense Reasoningaccuracy83.8%#37/732025-11-26source ↗
14MMLU-ProReasoning · Commonsense Reasoningaccuracy83.8%#37/73source ↗
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-VL-235B-A22B-Thinking actually performs.

Computer Vision
1
benchmark
avg rank #2.0
Multimodal
7
benchmarks
avg rank #9.1
Agentic AI
1
benchmark
avg rank #10.0
Computer Code
1
benchmark
avg rank #17.0
Reasoning
3
benchmarks
avg rank #29.5
§ 04 · Papers

1 paper with results for Qwen3-VL-235B-A22B-Thinking.

  1. 2025-11-26· 13 results

    Qwen3-VL Technical Report

§ 05 · Related models

Other Qwen models scored on Codesota.

Qwen3-VL-235B-A22B-Instruct
9 results · 1 SOTA
Qwen3-VL-8B-Instruct
9 results
Qwen3-Coder-Next
7 results
Qwen2.5-Plus
1 result
Qwen2.5-VL-72B
1 result
Qwen3-235B-A22B (Base)
1 result
Qwen3.5-122B-A10B
1 result
Qwen3.5-27B
1 result
§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
13
results
paperswithcode
1
result
0 of 14 rows marked verified.