Mistral Large 4
| Released | 2026-10-06 |
|---|---|
| Price per 1M | $0.70 in · $2.10 out |
| Overall score | 54.6 · rank 78 |
| Context window | 1,048,576 tokens |
| Provider | Mistral |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 54.6 | 78 | 31 |
| Overall: Coding | 55.3 | 67 | 23 |
| Overall: Reasoning | 54.7 | 81 | 13 |
| Overall: Agentic work | 55.8 | 72 | 20 |
| Overall: Frontend | 54.1 | 65 | 7 |
| Coding | 55.5 | 65 | 3 |
| Agents | 56.2 | 66 | 8 |
| Reasoning | 55.1 | 82 | 9 |
| Math | 58.1 | 43 | 2 |
| Knowledge | 47.9 | 104 | 2 |
| Frontend | 53.7 | 60 | 3 |
| General | 53.3 | 78 | 3 |
| Multimodal | 52.7 | 61 | 1 |
| Value vs price | +6.7 | 55 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 52.9 ±2.3 | 10 |
| High | 56.3 ±1.2 | 21 |
| Medium | 58.9 ±7.5 | 1 |
Evidence
Coding 55.5 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Coding | 44.4% | LiveBench | 2026-11-06 |
| IOI | 45.3% | Vals AI | 2026-10-29 |
| SWE-bench Multimodal | 33.1% | Vals AI | 2026-11-09 |
Agents 56.2 ±4.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 27.8% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Agentic | 9.2% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 0.6% | LiveBench | 2026-11-06 |
| EMB v1.1 (Excel financial modeling) | 69.0% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Research | 30.8% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 30.4% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 61.4% | Vals AI | 2026-11-09 |
| HLAB-Vals 1.1 (legal agent) | 17.5% | Vals AI | 2026-11-09 |
Reasoning 55.1 ±3.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 27.4% | Lech Mazur | 2026-11-10 |
| MysteryMechanism | 12.2% | Vals AI | 2026-11-09 |
| GPQA Diamond | 90.2% | Epoch AI | 2026-11-02 |
| CritPt | 11.1% | Epoch AI | 2026-11-11 |
| BioMysteryBench | 67.0% | Vals AI | 2026-11-09 |
| Chess Puzzles | 29.0% | Epoch AI | 2026-11-02 |
| LiveBench 2.0 Reasoning | 83.9% | LiveBench | 2026-11-06 |
| Mystery Game Puzzles | 20.0% | Epoch AI | 2026-11-02 |
| LiveBench 2.0 Data Analysis | 76.5% | LiveBench | 2026-11-06 |
Math 58.1 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ProofBench v1.1 | 10.0% | Vals AI | 2026-11-09 |
| OTIS Mock AIME 2024-2025 | 99.4% | Epoch AI | 2026-11-02 |
Knowledge 47.9 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 22.4% | Epoch AI | 2026-11-02 |
| Legal Research Bench | 31.7% | Vals AI | 2026-11-09 |
Frontend 53.7 ±5.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 60.7% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 78.4% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,562 | LMArena | 2026-11-09 |
General 53.3 ±2.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,423 | LMArena | 2026-11-09 |
| LLM Debate Benchmark | 1,448 | Lech Mazur | 2026-10-26 |
| Creative Story-Writing (Lech Mazur) | 26.0% | Lech Mazur | 2026-10-23 |
Multimodal 52.7 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,231 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| CritPt | 10.0% | Epoch AI | A stronger configuration result was used |
Names matched to this model
mistral-large-4, mistral-large-4-0-8, mistral-large-4-0-oss