Qwen3 VL 235B A22B Instruct

Qwen / Qwen

40scores
40benchmarks
$0.2 / $0.88 per 1M tokenscost in/out

Metadata

Qwen Open source

Aliases: qwen-qwen3-vl-235b-a22b-instruct, qwen/qwen3-vl-235b-a22b-instruct, qwen3-vl-235b-a22b-instruct

Benchmark Results

Benchmark Category Rank Score Sampled
Tau2-Bench Telecom Agentic 215 35.1% 2026-05-11
Terminal-Bench Hard Agentic 247 6.8% 2026-05-11
OpenUGI Alignment 202 45.56 2026-05-06
MultiPL-E Coding 3 0.861 2026-05-27
SciCode Coding 180 35.9% 2026-05-11
Arena-Hard v2 General Knowledge 5 0.77 2026-05-06
CSimpleQA General Knowledge 3 0.83 2026-05-06
MMLU-ProX General Knowledge 11 0.78 2026-05-06
MMLU-Redux General Knowledge 16 0.92 2026-05-06
Multi-IF Instruction Following 7 0.76 2026-05-06
Artificial Analysis Intelligence Index Intelligence 235 20.75 2026-05-11
Humanity's Last Exam Intelligence 235 6.3% 2026-05-11
MathVision Intelligence 33 66 2026-05-06
MMLU-Pro Intelligence 71 82.3% 2026-05-11
AIME 2025 Math 95 70.7% 2026-05-11
BLINK Multimodal 1 0.71 2026-05-06
CC-OCR Multimodal 2 0.82 2026-05-06
CharadesSTA Multimodal 1 0.65 2026-05-06
CharXiv-R Multimodal 23 0.62 2026-05-06
InfoVQAtest Multimodal 3 0.89 2026-05-06
LVBench Multimodal 6 0.68 2026-05-06
Math-VR Multimodal 2 65.0 2026-05-27
MLVU Multimodal 7 0.84 2026-05-06
MM-MT-Bench Multimodal 2 8.50 2026-05-06
MMLongBench-Doc Multimodal 6 57 2026-05-06
MuirBench Multimodal 6 0.73 2026-05-06
Physical AI Bench Understanding Multimodal 4 64.70 2026-05-06
VideoMME w/o sub. Multimodal 5 0.79 2026-05-06
VideoMMMU Multimodal 18 0.75 2026-05-06
OCRBench-V2 (en) OCR 3 0.67 2026-05-06
OCRBench-V2 (zh) OCR 3 0.62 2026-05-06
Artificial Analysis Openness Index Openness 61 50 2026-05-11
ERQA Reasoning 11 0.51 2026-05-06
GPQA Diamond Reasoning 195 71.2% 2026-05-11
CritPt Science 366 0% 2026-05-11
BFCL-v3 Tool Use 13 0.68 2026-05-06
ODinW Vision 3 0.49 2026-05-06
K-MetBench Weather 18 72.4% accuracy 2026-05-28
Creative Writing v3 Writing 4 0.86 2026-05-06
WritingBench Writing 5 0.85 2026-05-06