DeepSeek-V3 vs Mistral Small 3 (Non-Reasoning)
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Wins 1 of 5 areas
Facts
DeepSeek-V3 is the stronger all-rounder.Mistral Small 3 (Non-Reasoning) is cheaper and better at facts.
Scores updated · 17 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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.
- ReasoningHard problems that need careful thinking10DeepSeek-V31 of 2 tests · 1 tie
- CodingWriting and fixing software10DeepSeek-V31 of 1 test
- Long documentsFinding answers in very long texts10DeepSeek-V31 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-V31 of 1 test
- FactsGetting facts right instead of making them up01Mistral Small 3 (Non-Reasoning)1 of 1 test
Coding, facts, 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.
Mistral Small 3 (Non-Reasoning) costs 89% less for the same work.
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+19.3points ahead
- Code for real scientific research problemsSciCode+15.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+14.6points ahead
Where Mistral Small 3 (Non-Reasoning) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 19.365.546.2+19.3
- Humanity's Last Examtie4.73.8tie
FactsMistral Small 3 (Non-Reasoning)
- Vectara HHEM hallucination ratelower is betterMistral Small 3 (Non-Reasoning) by 16.15.1+1
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 14.64126.4+14.6
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)DeepSeek-V3 by 27.547.119.6+27.5
- vectara_avg_summary_lengthMistral Small 3 (Non-Reasoning) by 17.181.798.8+17.1
- AIR-Bench 2024DeepSeek-V3 by 840.832.8+8
- HarmBenchDeepSeek-V3 by 4.549.745.2+4.5
- bbqDeepSeek-V3 by 3.496.793.3+3.4
- AA IntelligenceDeepSeek-V3 by 39.76.7+3
- simple_safety_testsDeepSeek-V3 by 295.393.3+2
- XSTestDeepSeek-V3 by 1.897.195.3+1.8
- vectara_factual_consistencyMistral Small 3 (Non-Reasoning) by 193.994.9+1
- anthropic_red_teamtie97.196.4tie
- vectara_answer_ratetie97.597.9tie
Questions people ask
Which is better, DeepSeek-V3 or Mistral Small 3 (Non-Reasoning)?
DeepSeek-V3 wins four of the five areas where both have results: coding, reasoning, long documents and following instructions. Mistral Small 3 (Non-Reasoning) wins facts, and costs 89% less.
Which is better for coding?
DeepSeek-V3. It wins the one coding test both models report.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Mistral Small 3 (Non-Reasoning) costs $0.05 and $0.08. That makes Mistral Small 3 (Non-Reasoning) about 89% cheaper for the same work.
How do you compare the two?
We use the 17 benchmark tests both models have published scores on. The verdict counts the 6 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.