DeepSeek-V3 vs Qwen3 VL 4B (Reasoning)
Wins 5 of 6 areas
Coding · Reasoning · Facts · Long documents · Following instructions
Wins 1 of 6 areas
Agents
DeepSeek-V3 is the stronger all-rounder.Qwen3 VL 4B (Reasoning) is better at agents.
Scores updated · 24 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.
- FactsGetting facts right instead of making them up20DeepSeek-V32 of 2 tests
- CodingWriting and fixing software21DeepSeek-V32 of 3 tests
- ReasoningHard problems that need careful thinking10DeepSeek-V31 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts10DeepSeek-V31 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V31 of 1 test
- AgentsCarrying out multi-step tasks on its own01Qwen3 VL 4B (Reasoning)1 of 1 test
Agents, 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 DeepSeek-V3 pulls ahead
- Code for real scientific research problemsSciCode+21.9points ahead
- Reasons across sets of long documentsAA-LCR+19.4points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+16.1points ahead
Where Qwen3 VL 4B (Reasoning) pulls ahead
- Recent programming contest problemsLiveCodeBench v6+4.4points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- SciCodeDeepSeek-V3 by 21.93917.1+21.9
- Terminal-Bench HardDeepSeek-V3 by 13.715.21.5+13.7
- LiveCodeBench v6Qwen3 VL 4B (Reasoning) by 4.446.951.3+4.4
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 16.165.549.4+16.1
- Humanity's Last Examtie4.74.6tie
- CritPttie00tie
FactsDeepSeek-V3
- AA-Omniscience · AccuracyDeepSeek-V3 by 13.325.412.2+13.3
- AA-Omniscience · Non-hallucinationDeepSeek-V3 by 5.914.18.2+5.9
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 4.44136.6+4.4
Other results13 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.
- AIME 2024Qwen3 VL 4B (Reasoning) by 33.739.272.9+33.7
- τ²-Bench Telecom (AA run)DeepSeek-V3 by 31.647.115.5+31.6
- AA-OmniscienceDeepSeek-V3 by 27.7-40.7-68.4+27.7
- HMMT 2025Qwen3 VL 4B (Reasoning) by 25.627.553.1+25.6
- AIME 2025Qwen3 VL 4B (Reasoning) by 23.251.374.5+23.2
- Artificial Analysis Coding IndexDeepSeek-V3 by 16.3236.7+16.3
- SuperGPQADeepSeek-V3 by 6.953.746.8+6.9
- MMLU-ProXDeepSeek-V3 by 5.570.565+5.5
- IFEvalDeepSeek-V3 by 3.586.182.6+3.5
- MMLU-ReduxDeepSeek-V3 by 3.189.186+3.1
- AA IntelligenceDeepSeek-V3 by 2.79.77+2.7
- MMLU-ProDeepSeek-V3 by 2.375.973.6+2.3
- LiveCodeBenchQwen3 VL 4B (Reasoning) by 2.149.251.3+2.1
Questions people ask
Which is better, DeepSeek-V3 or Qwen3 VL 4B (Reasoning)?
DeepSeek-V3 wins five of the six areas where both have results: coding, reasoning, facts, long documents and following instructions. Qwen3 VL 4B (Reasoning) wins agents.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 3 coding tests both models report; Qwen3 VL 4B (Reasoning) wins 1.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 11 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.