Qwen3 VL 235B A22B Thinking

Qwen / Qwen

37scores
37benchmarks
$0.26 / $2.6 per 1M tokenscost in/out

Metadata

Qwen Open source

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

Benchmark Results

Benchmark Category Rank Score Sampled
OpenUGI Alignment 822 30.20 2026-05-06
EmbSpatialBench Embodied 3 0.84 2026-05-06
Design2Code Frontend Development 2 0.93 2026-05-06
MMLU-ProX General Knowledge 7 0.81 2026-05-06
MMLU-Redux General Knowledge 6 0.94 2026-05-06
Multi-IF Instruction Following 3 0.79 2026-05-06
MathVision Intelligence 22 74.60 2026-05-06
BLINK Multimodal 7 0.67 2026-05-06
CC-OCR Multimodal 5 0.81 2026-05-06
CharadesSTA Multimodal 2 0.64 2026-05-06
CharXiv-R Multimodal 20 0.66 2026-05-06
InfoVQAtest Multimodal 2 0.90 2026-05-06
LVBench Multimodal 8 0.64 2026-05-06
Math-VR Multimodal 1 66.8 2026-05-27
MLVU Multimodal 8 0.84 2026-05-06
MM-MT-Bench Multimodal 2 8.50 2026-05-06
MMLongBench-Doc Multimodal 7 56.20 2026-05-06
MuirBench Multimodal 2 0.80 2026-05-06
Physical AI Bench Understanding Multimodal 5 63.70 2026-05-06
SimpleVQA Multimodal 6 0.61 2026-05-06
VideoMME w/o sub. Multimodal 6 0.79 2026-05-06
VideoMMMU Multimodal 15 0.80 2026-05-06
ZEROBench Multimodal 6 0.04 2026-05-06
ZEROBench-Sub Multimodal 5 0.28 2026-05-06
OCRBench-V2 (en) OCR 4 0.67 2026-05-06
OCRBench-V2 (zh) OCR 1 0.64 2026-05-06
ERQA Reasoning 9 0.53 2026-05-06
CountBench Spatial Reasoning 6 0.94 2026-05-06
Hypersim Spatial Reasoning 4 0.11 2026-05-06
RefCOCO-avg Spatial Reasoning 3 0.92 2026-05-06
RefSpatialBench Spatial Reasoning 2 0.70 2026-05-06
SUNRGBD Spatial Reasoning 3 0.35 2026-05-06
BFCL-v3 Tool Use 5 0.72 2026-05-06
ODinW Vision 9 0.43 2026-05-06
K-MetBench Weather 3 84.4% accuracy 2026-05-28
Creative Writing v3 Writing 6 0.86 2026-05-06
WritingBench Writing 3 0.87 2026-05-06