DeepSeek-V3 vs Qwen3.5 0.8B
Wins 5 of 6 areas
Coding · Agents · Reasoning · Long documents · Following instructions
Wins 0 of 6 areas
—
DeepSeek-V3 is the stronger all-rounder.
Scores updated · 30 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.
- CodingWriting and fixing software30DeepSeek-V33 of 3 tests
- ReasoningHard problems that need careful thinking20DeepSeek-V32 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts20DeepSeek-V32 of 2 tests
- Following instructionsDoing exactly what it is asked20DeepSeek-V32 of 2 tests
- AgentsCarrying out multi-step tasks on its own10DeepSeek-V31 of 2 tests · 1 tie
- FactsGetting facts right instead of making them up11Even1 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
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+54.4points ahead
- Reasons across sets of long documentsAA-LCR+31.7points ahead
- Questions about very long textsLongBench v2+22.6points ahead
Where Qwen3.5 0.8B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+24.6points ahead
Every test, side by side
All 30 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- SciCodeDeepSeek-V3 by 39390+39
- Terminal-Bench 2.1DeepSeek-V3 by 16.916.90+16.9
- Terminal-Bench HardDeepSeek-V3 by 15.215.20+15.2
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 54.465.511.1+54.4
- Humanity's Last ExamDeepSeek-V3 by 3.64.71.1+3.6
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationQwen3.5 0.8B by 24.614.138.7+24.6
- AA-Omniscience · AccuracyDeepSeek-V3 by 21.325.44.2+21.3
Long documentsDeepSeek-V3
- AA-LCRDeepSeek-V3 by 31.740.79+31.7
- LongBench v2DeepSeek-V3 by 22.648.726.1+22.6
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 19.54121.5+19.5
- Multi-ChallengeDeepSeek-V3 by 12.531.418.9+12.5
Other results16 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 (Retail)DeepSeek-V3 by 62.169.17+62.1
- AIME 2025DeepSeek-V3 by 42.651.38.7+42.6
- C-EvalDeepSeek-V3 by 3686.550.5+36
- MMLU-ProXDeepSeek-V3 by 35.970.534.6+35.9
- MMMLUDeepSeek-V3 by 35.179.444.3+35.1
- MMLU-ProDeepSeek-V3 by 33.675.942.3+33.6
- AIME 2024DeepSeek-V3 by 33.539.25.7+33.5
- MATH-500 (EM)DeepSeek-V3 by 32.690.257.6+32.6
- SuperGPQADeepSeek-V3 by 32.453.721.3+32.4
- MMLU-ReduxDeepSeek-V3 by 29.689.159.5+29.6
- Artificial Analysis Coding IndexDeepSeek-V3 by 23230+23
- τ²-BenchDeepSeek-V3 by 18.232.514.3+18.2
- IFEvalDeepSeek-V3 by 14.986.171.2+14.9
- AA-OmniscienceDeepSeek-V3 by 13.8-40.7-54.5+13.8
- AA IntelligenceDeepSeek-V3 by 3.69.76.1+3.6
- τ²-Bench Telecom (AA run)tie47.147.7tie
Questions people ask
Which is better, DeepSeek-V3 or Qwen3.5 0.8B?
DeepSeek-V3 wins five of the six areas where both have results: coding, agents, reasoning, long documents and following instructions. Qwen3.5 0.8B wins none. They are level on facts.
Which is better for coding?
DeepSeek-V3. It wins 3 of the 3 coding tests both models report; Qwen3.5 0.8B wins none.
How do you compare the two?
We use the 30 benchmark tests both models have published scores on. The verdict counts the 14 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.