Mistral Large 2.1
| Released | 2024-11-18 |
|---|---|
| Price per 1M | $2.00 in · $6.00 out |
| Overall score | 35.7 · rank 214 |
| Context window | 131,072 tokens |
| Provider | Mistral |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 35.7 | 214 | 9 |
| Overall: Coding | 35.7 | 204 | 3 |
| Overall: Reasoning | 35.3 | 217 | 5 |
| Overall: Agentic work | 37.3 | 202 | 3 |
| Overall: Frontend | 34.4 | 203 | 1 |
| Coding | 34.4 | 192 | 1 |
| Agents | 38.5 | 161 | 1 |
| Reasoning | 37.2 | 212 | 1 |
| Math | 35.1 | 178 | 3 |
| Knowledge | 31.1 | 158 | 1 |
| General | 36.2 | 171 | 2 |
| Value vs price | −15.4 | 188 |
Evidence
Coding 34.4 ±5.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveCodeBench (Vals run) | 37.1% | Vals AI | 2026-09-01 |
Agents 38.5 ±3.6
Reasoning 37.2 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 51.3% | Epoch AI | 2025-02-25 |
| GPQA Diamond (Vals run) | 47.7% | Vals AI | 2026-09-01 |
Math 35.1 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 0.3% | Epoch AI | 2025-03-06 |
| MATH Level 5 | 50.3% | Epoch AI | 2025-02-25 |
| OTIS Mock AIME 2024-2025 | 7.8% | Epoch AI | 2025-02-25 |
Knowledge 31.1 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 69.7% | Vals AI | 2026-09-01 |
General 36.2 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Creative Writing v3 | 982 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,306 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| BFCL v4 | 31.8% | BFCL | A stronger configuration result was used |
Names matched to this model
mistral-large-2-1, mistral-large-2411, mistral-large-instruct-2411