Qwen3 VL 4B (Reasoning) vs Step3 VL 10B
Wins 2 of 7 areas
Agents · Long documents
Wins 5 of 7 areas
Coding · Reasoning · Facts · Images and charts · Following instructions
Step3 VL 10B is the stronger all-rounder.Qwen3 VL 4B (Reasoning) is better at agents.
Scores updated · 27 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 video05Step3 VL 10B5 of 5 tests
- ReasoningHard problems that need careful thinking02Step3 VL 10B2 of 3 tests · 1 tie
- CodingWriting and fixing software02Step3 VL 10B2 of 2 tests
- FactsGetting facts right instead of making them up02Step3 VL 10B2 of 2 tests
- Following instructionsDoing exactly what it is asked01Step3 VL 10B1 of 1 test
- AgentsCarrying out multi-step tasks on its own10Qwen3 VL 4B (Reasoning)1 of 1 test
- Long documentsFinding answers in very long texts10Qwen3 VL 4B (Reasoning)1 of 1 test
Agents, long documents and following instructions rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Step3 VL 10B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+19.6points ahead
- Code for real scientific research problemsSciCode+14points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+13.6points ahead
Where Qwen3 VL 4B (Reasoning) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 27 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingStep3 VL 10B
- SciCodeStep3 VL 10B by 1417.131.1+14
- Terminal-Bench HardStep3 VL 10B by 3.81.55.3+3.8
ReasoningStep3 VL 10B
- GPQA DiamondStep3 VL 10B by 19.649.469+19.6
- Humanity's Last ExamStep3 VL 10B by 6.24.610.8+6.2
- CritPttie00tie
FactsStep3 VL 10B
- AA-Omniscience · Non-hallucinationStep3 VL 10B by 8.58.216.7+8.5
- AA-Omniscience · AccuracyStep3 VL 10B by 1.112.213.3+1.1
Images and chartsStep3 VL 10B
Long documentsQwen3 VL 4B (Reasoning)
- AA-LCRQwen3 VL 4B (Reasoning) by 21.321.30+21.3
Following instructionsStep3 VL 10B
- IFBenchStep3 VL 10B by 13.636.650.2+13.6
Other results12 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.
- HMMT 2025Step3 VL 10B by 3953.192.1+39
- LiveCodeBenchStep3 VL 10B by 25.151.376.4+25.1
- AIME 2025Step3 VL 10B by 13.274.587.7+13.2
- MATH-VisionStep3 VL 10B by 10.86070.8+10.8
- All-Angles-BenchStep3 VL 10B by 10.546.757.2+10.5
- AA-OmniscienceStep3 VL 10B by 9.4-68.4-59+9.4
- AA Agentic IndexQwen3 VL 4B (Reasoning) by 914.45.4+9
- Artificial Analysis Coding IndexStep3 VL 10B by 7.26.713.9+7.2
- AI2DStep3 VL 10B by 4.584.989.3+4.5
- ScreenSpot-Pro (No tools)Step3 VL 10B by 2.449.251.5+2.4
- AA Intelligencetie77.7tie
- τ²-Bench Telecom (AA run)tie15.516.1tie
Questions people ask
Which is better, Qwen3 VL 4B (Reasoning) or Step3 VL 10B?
Step3 VL 10B wins five of the seven areas where both have results: coding, reasoning, facts, images and charts and following instructions. Qwen3 VL 4B (Reasoning) wins agents and long documents.
Which is better for coding?
Step3 VL 10B. It wins 2 of the 2 coding tests both models report; Qwen3 VL 4B (Reasoning) wins none.
How do you compare the two?
We use the 27 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 12 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.