DeepSeek-R1 vs Mistral Small 3 (Non-Reasoning)
Wins 4 of 5 areas
Coding · Reasoning · Long documents · Following instructions
Wins 1 of 5 areas
Facts
DeepSeek-R1 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 thinking20DeepSeek-R12 of 2 tests
- CodingWriting and fixing software10DeepSeek-R11 of 1 test
- Long documentsFinding answers in very long texts10DeepSeek-R11 of 1 test
- Following instructionsDoing exactly what it is asked10DeepSeek-R11 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 98% 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-R1 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+24.6points ahead
- Code for real scientific research problemsSciCode+14.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+12.6points 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-R1
- GPQA DiamondDeepSeek-R1 by 24.670.846.2+24.6
- Humanity's Last ExamDeepSeek-R1 by 4.78.53.8+4.7
FactsMistral Small 3 (Non-Reasoning)
- Vectara HHEM hallucination ratelower is betterMistral Small 3 (Non-Reasoning) by 6.211.35.1+6.2
Following instructionsDeepSeek-R1
- IFBenchDeepSeek-R1 by 12.63926.4+12.6
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.
- AIR-Bench 2024DeepSeek-R1 by 20.152.932.8+20.1
- τ²-Bench Telecom (AA run)Mistral Small 3 (Non-Reasoning) by 8.211.419.6+8.2
- vectara_factual_consistencyMistral Small 3 (Non-Reasoning) by 6.288.794.9+6.2
- vectara_avg_summary_lengthMistral Small 3 (Non-Reasoning) by 5.393.598.8+5.3
- AA IntelligenceDeepSeek-R1 by 4.711.46.7+4.7
- simple_safety_testsDeepSeek-R1 by 4.79893.3+4.7
- bbqDeepSeek-R1 by 3.396.693.3+3.3
- HarmBenchDeepSeek-R1 by 2.747.945.2+2.7
- vectara_answer_ratetie9797.9tie
- XSTesttie94.495.3tie
- anthropic_red_teamtie97.296.4tie
Questions people ask
Which is better, DeepSeek-R1 or Mistral Small 3 (Non-Reasoning)?
DeepSeek-R1 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 98% less.
Which is better for coding?
DeepSeek-R1. It wins the one coding test both models report.
Which is cheaper?
DeepSeek-R1 costs $2.00 per million input tokens and $4.00 per million output tokens; Mistral Small 3 (Non-Reasoning) costs $0.05 and $0.08. That makes Mistral Small 3 (Non-Reasoning) about 98% 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.