DeepSeek-V4-Pro 0813 vs Mistral Large 4
Wins 4 of 7 areas
Reasoning · Facts · Math · Following instructions
Wins 2 of 7 areas
Coding · Long documents
DeepSeek-V4-Pro 0813 wins more areas, narrowly.Mistral Large 4 is cheaper and better at coding.
Scores updated · 31 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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 thinking30DeepSeek-V4-Pro 08133 of 3 tests
- MathCompetition and research-level math20DeepSeek-V4-Pro 08132 of 3 tests · 1 tie
- FactsGetting facts right instead of making them up21DeepSeek-V4-Pro 08132 of 3 tests
- Following instructionsDoing exactly what it is asked10DeepSeek-V4-Pro 08131 of 1 test
- CodingWriting and fixing software03Mistral Large 43 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts01Mistral Large 41 of 1 test
- AgentsCarrying out multi-step tasks on its own11Even1 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 Large 4 costs 47% 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-V4-Pro 0813 pulls ahead
- Short factual questions, answered correctlySimpleQA Verified+30.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+23.3points ahead
- Research-level physics problemsCritPt+8points ahead
Where Mistral Large 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+52.9points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+11.5points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+10.6points ahead
Every test, side by side
All 31 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingMistral Large 4
- Terminal-Bench 2.1Mistral Large 4 by 11.578.790.2+11.5
- SciCodeMistral Large 4 by 3.25154.2+3.2
- LiveBench · Agentic CodingMistral Large 4 by 2.25557.2+2.2
- LiveBench · Codingtie77.277.2tie
AgentsEven
- Terminal-Bench 4.0Mistral Large 4 by 10.614.124.7+10.6
- GDPValDeepSeek-V4-Pro 0813 by 1.347.546.2+1.3
ReasoningDeepSeek-V4-Pro 0813
- CritPtDeepSeek-V4-Pro 0813 by 81810+8
- Humanity's Last ExamDeepSeek-V4-Pro 0813 by 64135+6
- LiveBench · ReasoningDeepSeek-V4-Pro 0813 by 1.985.883.9+1.9
FactsDeepSeek-V4-Pro 0813
- AA-Omniscience · Non-hallucinationMistral Large 4 by 52.95.258.1+52.9
- SimpleQA VerifiedDeepSeek-V4-Pro 0813 by 30.552.922.4+30.5
- AA-Omniscience · AccuracyDeepSeek-V4-Pro 0813 by 23.349.125.8+23.3
MathDeepSeek-V4-Pro 0813
- FrontierMath Tiers 1-3 (v2)DeepSeek-V4-Pro 0813 by 664.658.6+6
- LiveBench · MathematicsDeepSeek-V4-Pro 0813 by 1.595.193.6+1.5
- FrontierMath Tier 4tie26.826.8tie
Following instructionsDeepSeek-V4-Pro 0813
- LiveBench · Instruction FollowingDeepSeek-V4-Pro 0813 by 2.967.764.8+2.9
Other results14 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.
- livebench_languageDeepSeek-V4-Pro 0813 by 32.582.149.6+32.5
- JailbreakBench (cyber subset): safe-response rateMistral Large 4 by 32.464.997.3+32.4
- StrongREJECT (cyber subset): refusal rateMistral Large 4 by 15.277.492.6+15.2
- GDP (Surge AI)Mistral Large 4 by 6.211.417.6+6.2
- AA-OmniscienceDeepSeek-V4-Pro 0813 by 6.10.8-5.3+6.1
- AgentHarm (cyber subset): 100 minus harm scoreMistral Large 4 by 595100+5
- CritPt v2 HardMistral Large 4 by 3.523.527+3.5
- livebench_data_analysisDeepSeek-V4-Pro 0813 by 2.779.276.5+2.7
- CritPt v2 (Hard Subset)Mistral Large 4 by 2.523.526+2.5
- AA IntelligenceMistral Large 4 by 2.43638.4+2.4
- HLE-DiamondDeepSeek-V4-Pro 0813 by 2.219.517.3+2.2
- Terminal-Bench-Science 0.1DeepSeek-V4-Pro 0813 by 1.45.74.3+1.4
- CyberGymDeepSeek-V4-Pro 0813 by 1.383.382+1.3
- BeyondAIMEtie90.190.6tie
Questions people ask
Which is better, DeepSeek-V4-Pro 0813 or Mistral Large 4?
DeepSeek-V4-Pro 0813 wins four of the seven areas where both have results: reasoning, facts, math and following instructions. Mistral Large 4 wins coding and long documents, and costs 47% less. They are level on agents.
Which is better for coding?
Mistral Large 4. It wins 3 of the 4 coding tests both models report; DeepSeek-V4-Pro 0813 wins none, and 1 is a tie.
Which is cheaper?
DeepSeek-V4-Pro 0813 costs $1.32 per million input tokens and $3.96 per million output tokens; Mistral Large 4 costs $0.70 and $2.10. That makes Mistral Large 4 about 47% cheaper for the same work.
How do you compare the two?
We use the 31 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 14 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.