Qwen3.5 35B A3B vs Qwen3 VL 4B (Reasoning)
Wins 6 of 7 areas
Coding · Reasoning · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Qwen3.5 35B A3B is the stronger all-rounder.
Scores updated · 42 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 video50Qwen3.5 35B A3B5 of 5 tests
- CodingWriting and fixing software30Qwen3.5 35B A3B3 of 3 tests
- ReasoningHard problems that need careful thinking20Qwen3.5 35B A3B2 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up20Qwen3.5 35B A3B2 of 2 tests
- Long documentsFinding answers in very long texts10Qwen3.5 35B A3B1 of 1 test
- Following instructionsDoing exactly what it is asked10Qwen3.5 35B A3B1 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 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 Qwen3.5 35B A3B pulls ahead
- Reasons across sets of long documentsAA-LCR+50.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+35.9points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+35.1points ahead
Where Qwen3 VL 4B (Reasoning) pulls ahead
- Real work tasks from 44 professionsGDPVal+8.2points ahead
Every test, side by side
All 42 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 35B A3B
- Terminal-Bench HardQwen3.5 35B A3B by 2526.51.5+25
- LiveCodeBench v6Qwen3.5 35B A3B by 23.374.651.3+23.3
- SciCodeQwen3.5 35B A3B by 20.637.717.1+20.6
AgentsEven
- OSWorld-VerifiedQwen3.5 35B A3B by 23.154.531.4+23.1
- GDPValQwen3 VL 4B (Reasoning) by 8.25.613.8+8.2
ReasoningQwen3.5 35B A3B
- GPQA DiamondQwen3.5 35B A3B by 35.184.549.4+35.1
- Humanity's Last ExamQwen3.5 35B A3B by 16.4214.6+16.4
- CritPttie0.90tie
FactsQwen3.5 35B A3B
- AA-Omniscience · AccuracyQwen3.5 35B A3B by 7.920.112.2+7.9
- AA-Omniscience · Non-hallucinationQwen3.5 35B A3B by 6.414.68.2+6.4
Images and chartsQwen3.5 35B A3B
- CharXiv (RQ)Qwen3.5 35B A3B by 27.277.550.3+27.2
- MMMU-ProQwen3.5 35B A3B by 20.772.752+20.7
- OCRBenchQwen3.5 35B A3B by 10.29180.8+10.2
- MMStarQwen3.5 35B A3B by 8.781.973.2+8.7
- MathVistaQwen3.5 35B A3B by 6.786.279.5+6.7
Following instructionsQwen3.5 35B A3B
- IFBenchQwen3.5 35B A3B by 35.972.536.6+35.9
Other results25 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)Qwen3.5 35B A3B by 73.789.215.5+73.7
- HMMT 2025Qwen3.5 35B A3B by 36.189.253.1+36.1
- Artificial Analysis Coding IndexQwen3.5 35B A3B by 30.3376.7+30.3
- MATH-VisionQwen3.5 35B A3B by 23.983.960+23.9
- AA-OmniscienceQwen3.5 35B A3B by 20.3-48.1-68.4+20.3
- ScreenSpot-Pro (No tools)Qwen3.5 35B A3B by 19.468.649.2+19.4
- RefSpatial-BenchQwen3.5 35B A3B by 18.263.545.3+18.2
- LVBenchQwen3.5 35B A3B by 17.971.453.5+17.9
- ERQAQwen3.5 35B A3B by 17.564.847.3+17.5
- SuperGPQAQwen3.5 35B A3B by 16.663.446.8+16.6
- MMLU-ProXQwen3.5 35B A3B by 168165+16
- IncludeQwen3.5 35B A3B by 15.179.764.6+15.1
- AA IntelligenceQwen3.5 35B A3B by 12.319.37+12.3
- MMLU-ProQwen3.5 35B A3B by 11.785.373.6+11.7
- VideoMMMUQwen3.5 35B A3B by 1180.469.4+11
- RealWorldQAQwen3.5 35B A3B by 10.984.173.2+10.9
- IFEvalQwen3.5 35B A3B by 9.391.982.6+9.3
- AI2DQwen3.5 35B A3B by 7.792.684.9+7.7
- MMLU-ReduxQwen3.5 35B A3B by 7.393.386+7.3
- CC-OCRQwen3.5 35B A3B by 6.980.773.8+6.9
- OCRBench v2 (Chinese)Qwen3.5 35B A3B by 5.961.755.8+5.9
- MV-BenchQwen3.5 35B A3B by 5.574.869.3+5.5
- HallusionBenchQwen3.5 35B A3B by 3.867.964.1+3.8
- AA Agentic IndexQwen3 VL 4B (Reasoning) by 2.611.814.4+2.6
- EmbSpatial-BenchQwen3.5 35B A3B by 2.483.180.7+2.4
Questions people ask
Which is better, Qwen3.5 35B A3B or Qwen3 VL 4B (Reasoning)?
Qwen3.5 35B A3B wins six of the seven areas where both have results: coding, reasoning, facts, images and charts, long documents and following instructions. Qwen3 VL 4B (Reasoning) wins none. They are level on agents.
Which is better for coding?
Qwen3.5 35B A3B. It wins 3 of the 3 coding tests both models report; Qwen3 VL 4B (Reasoning) wins none.
How do you compare the two?
We use the 42 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 25 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.