Mistral Large 4
Mistral·Released Oct 6, 2026
Updated Oct 8, 9:18 PM ET
The score is on the board's scale (reference average 50, about 15 points per standard deviation), not a percentage.
By domain
Each domain is scored on the same scale as the overall score. Coverage is the share of the domain's kinds of evaluation with a result; it says how much evidence there is, not how good the model is.
Every result behind the score
The result as the evaluator publishes it, and the reading it gives on the board's scale. A hard evaluation can give a high reading for a modest result; results near 95% or 5% only say "at least" or "at most".
Coding
5 results · 56.9- Vibe Code BenchVals AI · high effort78.4%Reading 62.8
- LiveBench CodingLiveBench · high effort67.2%Reading 59.7
- Terminal-Bench 4.0Vals AI · high effort22.7%Reading 59.2
- Code MigrationVals AI · high effort30.6%Reading 52.4
- Vibe Code Bench 1–100Vals AI · high effort14.3%Reading 52.4
Research and reasoning
3 results · 44.0- LiveBench ReasoningLiveBench · high effort88.8%Reading 58.9
- MysteryMechanismVals AI · high effort12.2%Reading 37.5
- ProofBenchVals AI · high effort10.0%Reading 31.4
Professional work
7 results · 59.5- Harvey Legal Agent BenchmarkVals AI · high effort15.8%Reading 90.0
- Tax Agent BenchVals AI · high effort30.4%Reading 63.6
- Finance AgentVals AI · high effort54.7%Reading 62.8
- LiveBench Data AnalysisLiveBench · high effort76.5%Reading 62.5
- EMBVals AI · high effort56.2%Reading 52.6
- Legal Research BenchVals AI · high effort31.7%Reading 52.1
- MedCodeVals AI · high effort40.7%Reading 36.3
Knowledge and accuracy
2 results · 33.4- LiveBench Instruction FollowingLiveBench · high effort64.8%Reading 41.9
- LiveBench LanguageLiveBench · high effortCapped49.6%Reading -5.8
Shown, not scored
Composite indices, saturated or older evaluations, evaluations still being checked, and vision, writing and multilingual results. They do not move the score.
- IOIVals AI · CodingReference only45.3%
- BioMysteryBenchVals AI · Research and reasoningWatching67.0%
- MedScribeVals AI · Professional workWatching80.4%
- LiveBench averageLiveBench · Composite indicesReference only71.8%
- Vals IndexVals AI · Composite indicesReference only48.0%
No result yet
Scored evaluations this model has not taken. A missing result neither adds nor subtracts.
- Terminal-Bench 4.0 (AA run) · Artificial Analysis
- ProgramBench · Vals AI
- CyberBench Patch · Vals AI
- APEX-SWE · Mercor
- SciCode · Artificial Analysis
- FrontierMath Tiers 1–3 · Epoch AI
- FrontierMath Tier 4 · Epoch AI
- Chess Puzzles · Epoch AI
- Mystery Game Puzzles · Epoch AI
- Terminal-Bench Science · Vals AI
- Humanity's Last Exam (AA run) · Artificial Analysis
- APEX-Agents · Mercor
- τ²-Bench Telecom (AA run) · Artificial Analysis
- τ-Bench Banking (AA run) · Artificial Analysis
- SimpleQA Verified · Epoch AI
- BullshitBench · BullshitBench
- AA-LCR · Artificial Analysis
- IFBench (AA run) · Artificial Analysis
- Arena Text · LMArena