Qwen3 VL 235B A22B Reasoning vs Step3 VL 10B
Wins 5 of 6 areas
Coding · Reasoning · Images and charts · Long documents · Following instructions
Wins 0 of 6 areas
—
Qwen3 VL 235B A22B Reasoning is the stronger all-rounder.
Scores updated · 26 tests both models report · How we compare
Where each one wins
Tests won in each of the six areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- Images and chartsUnderstanding pictures, charts and video31Qwen3 VL 235B A22B Reasoning3 of 6 tests · 2 ties
- ReasoningHard problems that need careful thinking20Qwen3 VL 235B A22B Reasoning2 of 3 tests · 1 tie
- CodingWriting and fixing software20Qwen3 VL 235B A22B Reasoning2 of 2 tests
- Long documentsFinding answers in very long texts10Qwen3 VL 235B A22B Reasoning1 of 1 test
- Following instructionsDoing exactly what it is asked10Qwen3 VL 235B A22B Reasoning1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3 VL 235B A22B Reasoning pulls ahead
- Code for real scientific research problemsSciCode+8.8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8.2points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+7.6points ahead
Where Step3 VL 10B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+1.9points ahead
- Reads text in imagesOCRBench+1.5points ahead
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3 VL 235B A22B Reasoning
- SciCodeQwen3 VL 235B A22B Reasoning by 8.839.931.1+8.8
- Terminal-Bench HardQwen3 VL 235B A22B Reasoning by 6.111.45.3+6.1
ReasoningQwen3 VL 235B A22B Reasoning
- GPQA DiamondQwen3 VL 235B A22B Reasoning by 8.277.269+8.2
- Humanity's Last ExamQwen3 VL 235B A22B Reasoning by 1.111.910.8+1.1
- CritPttie00tie
FactsEven
- AA-Omniscience · AccuracyQwen3 VL 235B A22B Reasoning by 7.620.913.3+7.6
- AA-Omniscience · Non-hallucinationStep3 VL 10B by 1.914.816.7+1.9
Images and chartsQwen3 VL 235B A22B Reasoning
Long documentsQwen3 VL 235B A22B Reasoning
- AA-LCRQwen3 VL 235B A22B Reasoning by 63.763.70+63.7
Following instructionsQwen3 VL 235B A22B Reasoning
- IFBenchQwen3 VL 235B A22B Reasoning by 6.356.550.2+6.3
Other results11 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- τ²-Bench Telecom (AA run)Qwen3 VL 235B A22B Reasoning by 3854.116.1+38
- HMMT 2025Step3 VL 10B by 14.777.492.1+14.7
- AA-OmniscienceQwen3 VL 235B A22B Reasoning by 12.5-46.5-59+12.5
- ScreenSpot-Pro (No tools)Qwen3 VL 235B A22B Reasoning by 10.261.851.5+10.2
- OSWorld-GQwen3 VL 235B A22B Reasoning by 9.368.359+9.3
- LiveCodeBenchStep3 VL 10B by 6.969.576.4+6.9
- AA IntelligenceQwen3 VL 235B A22B Reasoning by 5.713.47.7+5.7
- MATH-VisionQwen3 VL 235B A22B Reasoning by 3.874.670.8+3.8
- AIME 2025Qwen3 VL 235B A22B Reasoning by 289.787.7+2
- MMBench (EN)tie92.792.4tie
- AI2Dtie89.289.3tie
Questions people ask
Which is better, Qwen3 VL 235B A22B Reasoning or Step3 VL 10B?
Qwen3 VL 235B A22B Reasoning wins five of the six areas where both have results: coding, reasoning, images and charts, long documents and following instructions. Step3 VL 10B wins none. They are level on facts.
Which is better for coding?
Qwen3 VL 235B A22B Reasoning. It wins 2 of the 2 coding tests both models report; Step3 VL 10B wins none.
How do you compare the two?
We use the 26 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.