DeepSeek-V3 vs Mistral Large 2
Wins 4 of 6 areas
Coding · Reasoning · Long documents · Following instructions
Wins 0 of 6 areas
—
DeepSeek-V3 is the stronger all-rounder.
Scores updated · 23 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 software20DeepSeek-V32 of 2 tests
- ReasoningHard problems that need careful thinking21DeepSeek-V32 of 4 tests · 1 tie
- 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 own00Even0 each · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
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.
DeepSeek-V3 costs 86% 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
- Reasons across sets of long documentsAA-LCR+38.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+16.9points ahead
- Code for real scientific research problemsSciCode+9.8points ahead
Where Mistral Large 2 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+18.2points ahead
- Common-sense trick questionsSimpleBench+3.6points ahead
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingDeepSeek-V3
- SciCodeDeepSeek-V3 by 9.83929.2+9.8
- Terminal-Bench HardDeepSeek-V3 by 9.115.26.1+9.1
ReasoningDeepSeek-V3
- GPQA DiamondDeepSeek-V3 by 16.965.548.6+16.9
- SimpleBenchMistral Large 2 by 3.618.922.5+3.6
- Humanity's Last ExamDeepSeek-V3 by 1.44.73.3+1.4
- CritPttie00tie
FactsEven
- AA-Omniscience · Non-hallucinationMistral Large 2 by 18.214.132.3+18.2
- AA-Omniscience · AccuracyDeepSeek-V3 by 5.625.419.9+5.6
Following instructionsDeepSeek-V3
- IFBenchDeepSeek-V3 by 9.84131.2+9.8
Other results12 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.
- HumanEvalMistral Large 2 by 26.865.292+26.8
- MATHDeepSeek-V3 by 22.590.267.7+22.5
- τ²-Bench Telecom (AA run)DeepSeek-V3 by 16.447.130.7+16.4
- MMLUDeepSeek-V3 by 1688.572.5+16
- Artificial Analysis Coding IndexDeepSeek-V3 by 9.22313.8+9.2
- AA-OmniscienceMistral Large 2 by 6.3-40.7-34.4+6.3
- AIR-Bench 2024DeepSeek-V3 by 5.540.835.3+5.5
- OpenBookQADeepSeek-V3 by 2.295.493.2+2.2
- AA IntelligenceDeepSeek-V3 by 2.19.77.6+2.1
- NarrativeQADeepSeek-V3 by 1.779.677.9+1.7
- naturalquestions_closedbookDeepSeek-V3 by 1.446.745.3+1.4
- GSM8KDeepSeek-V3 by 19493+1
Questions people ask
Which is better, DeepSeek-V3 or Mistral Large 2?
DeepSeek-V3 wins four of the six areas where both have results: coding, reasoning, long documents and following instructions. Mistral Large 2 wins none. They are level on agents and facts.
Which is better for coding?
DeepSeek-V3. It wins 2 of the 2 coding tests both models report; Mistral Large 2 wins none.
Which is cheaper?
DeepSeek-V3 costs $0.24 per million input tokens and $0.90 per million output tokens; Mistral Large 2 costs $2.00 and $6.00. That makes DeepSeek-V3 about 86% cheaper for the same work.
How do you compare the two?
We use the 23 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 12 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.