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-InstructQwen14 results · 13 benchmarks
Model card

Qwen3-VL-235B-A22B-Instruct.

QwenLarge language model1 current SOTA

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

§ 02 · Benchmarks

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

#BenchmarkArea · TaskMetricValueRankDateSource
01DocVQAComputer Vision · Document Understandinganls97.1%#1/21source ↗
02MVBenchMultimodal · Video Understandingaccuracy76.5%#4/20source ↗
03MMBenchMultimodal · Visual Question Answeringaccuracy89.3%#5/20source ↗
04Video-MMEMultimodal · Video Understandingaccuracy79.2%#7/24source ↗
05RealWorldQAMultimodal · Visual Question Answeringaccuracy79.2%#9/23source ↗
06MMStarMultimodal · Image-Text-to-Textaccuracy78.4%#10/21source ↗
07MMMUMultimodal · Image-Text-to-Textaccuracy78.7%#12/36source ↗
08AIME 2025Reasoning · Mathematical Reasoningaccuracy74.7%#17/22source ↗
09OSWorldAgentic AI · Web & Desktop Agentssuccess-rate31.6%#18/28source ↗
10MMMU-ProMultimodal · Visual Question Answeringaccuracy68.1%#19/31source ↗
11LiveCodeBenchComputer Code · Code Generationpass-154.3%#22/24source ↗
12MMLU-ProReasoning · Commonsense Reasoningaccuracy81.8%#41/732025-11-26source ↗
13MMLU-ProReasoning · Commonsense Reasoningaccuracy81.8%#41/73source ↗
14GPQA DiamondReasoning · Multi-step Reasoningaccuracy74.3%#42/74source ↗
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-Instruct actually performs.

Computer Vision
1
benchmark
avg rank #1.0 · 1 SOTA
Multimodal
7
benchmarks
avg rank #9.4
Agentic AI
1
benchmark
avg rank #18.0
Computer Code
1
benchmark
avg rank #22.0
Reasoning
3
benchmarks
avg rank #35.3
§ 04 · Papers

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

  1. 2025-11-26· 13 results

    Qwen3-VL Technical Report

§ 05 · Related models

Other Qwen models scored on Codesota.

Qwen3-VL-235B-A22B-Thinking
9 results
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.