DeepSeek-V3 vs Mistral Small 3.1
Wins 4 of 6 areas
Coding · Reasoning · Long documents · Following instructions
Wins 1 of 6 areas
Agents
DeepSeek-V3 is the stronger all-rounder.Mistral Small 3.1 is cheaper and better at agents.
Scores updated · 17 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 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 own01Mistral Small 3.11 of 3 tests · 2 ties
- FactsGetting facts right instead of making them up11Even1 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.
Mistral Small 3.1 costs 75% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where DeepSeek-V3 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+20.1points ahead
- Reasons across sets of long documentsAA-LCR+18.4points ahead
- Code for real scientific research problemsSciCode+11.2points ahead
Where Mistral Small 3.1 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+9.3points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+8.3points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+2.7points ahead
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.
CodingDeepSeek-V3
- SciCodeDeepSeek-V3 by 11.23927.8+11.2
- Terminal-Bench 2.1Mistral Small 3.1 by 9.316.926.2+9.3
- Terminal-Bench HardDeepSeek-V3 by 7.615.27.6+7.6
AgentsMistral Small 3.1
- τ-Bench V3 · BankingMistral Small 3.1 by 2.74.77.4+2.7
- GDPValtie00tie
- Terminal-Bench 4.0tie00tie
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 20.165.545.4+20.1
- Humanity's Last Examtie4.74.3tie
- CritPttie00tie
FactsEven
- AA-Omniscience · AccuracyDeepSeek-V3 by 10.425.415.1+10.4
- AA-Omniscience · Non-hallucinationMistral Small 3.1 by 8.314.122.4+8.3
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 11.14129.9+11.1
Other results4 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 2247.125.1+22
- AA-OmniscienceDeepSeek-V3 by 10-40.7-50.8+10
- Artificial Analysis Coding IndexMistral Small 3.1 by 3.32326.3+3.3
- AA IntelligenceDeepSeek-V3 by 2.69.77.1+2.6
Questions people ask
Which is better, DeepSeek-V3 or Mistral Small 3.1?
DeepSeek-V3 wins four of the six areas where both have results: coding, reasoning, long documents and following instructions. Mistral Small 3.1 wins agents, and costs 75% less. They are level on facts.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 3 coding tests both models report; Mistral Small 3.1 wins 1.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Mistral Small 3.1 costs $0.11 and $0.17. That makes Mistral Small 3.1 about 75% 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 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 4 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.