Mistral AIMistral Large 2.1
Mistral Large 2.1 is a Mistral AI open-weights model, released 18 Nov 2024. Its best configuration ranks #590 of 785 on the BenchLeader Index at 42.5 ±3.7, in the lower half. The ± is the point: 285 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (49) and lowest in coding (31). Last measured 22 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 18 Nov 2024
- Overall index43
- Reasoning41
- Coding31
- Agents & tools46
- Maths40
- Knowledge40
- Instruction following49
- Human preference46
- Composite38
Versions
Mistral AI has shipped 5 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Mistral Large 4 | 6 Oct 2026 | 56.7 | #196 |
| Mistral Large 3 | 2 Dec 2025 | 45.4 | #512 |
| Mistral Large 2.1this page | 18 Nov 2024 | 42.5 | #590 |
| Mistral Large 2 | 24 Jul 2024 | 40.7 | #652 |
| Mistral Large 24.02 | 26 Feb 2024 | 40.2 | #660 |
How its index has moved
8 Sept 2026 to 18 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 51.3%#212 | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | 1313#248 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 48.6%#436 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 3.3%#599 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | 47.7%#118 | Vals AI | |
| GPQA Diamond (HELM)not in index | 43.5%#43 | HELM Capabilities | |
| CritPt | 0.0%#315 | Artificial Analysis | |
| DTBenchnot in index | 60.8%#184 | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | 61.5%#64 | ForecastBench |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1346#247 | Arena (LMArena) | |
| LiveCodeBench | 37.1%#127 | Vals AI |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 6.1%#266 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 30.7%#255 | Artificial Analysis | |
| BFCL Overall | 38.4%#36 | Berkeley Function Calling Leaderboard | |
| BrowseCompnot in index | 0.6%#26 | OpenAI |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 7.8%#234 | Epoch AI Benchmarking Hub | |
| MATH Level 5 | 50.3%#53 | Epoch AI Benchmarking Hub | |
| AIME (Vals) | 9.2%#87 | Vals AI | |
| MGSM | 87.2%#57 | Vals AI | |
| Omni-MATH (HELM) | 28.1%#47 | HELM Capabilities | |
| MATH 500not in index | 74.4%#44 | Vals AI | |
| Arena Maths | 1282#243 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -34.4#298 | Artificial Analysis | |
| MMLU-Pro | 69.7%#114 | Vals AI | |
| TaxEval | 63.8%#113 | Vals AI | |
| MedQA | 76.2%#74 | Vals AI | |
| MMLU-Pro (HELM)not in index | 59.9%#49 | HELM Capabilities | |
| AA-Omniscience: accuracynot in index | 19.9%#308 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 32.3%#209 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 31.2%#357 | Artificial Analysis | |
| IFEval (HELM) | 87.6%#13 | HELM Capabilities | |
| WildBench (HELM) | 80.1%#33 | HELM Capabilities | |
| Arena Instruction Followingnot in index | 1295#241 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1306#250 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1276#241 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1294#246 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1305#252 | Arena (LMArena) |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 128.6#152 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 7.6#466 | Artificial Analysis | |
| HELM Capabilities meannot in index | 59.8%#45 | HELM Capabilities |
Safety & honesty
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MASKnot in index | 47.5%#58 | Scale AI SEAL |
More from Mistral AI
See also
Questions people ask
- What are Mistral Large 2.1's benchmark scores?
- As of 25 Oct 2026, Mistral Large 2.1 scores 42.5 ±3.7 on the BenchLeader Index, strongest in instruction following (49) and weakest in coding (31). That rests on 22 independent benchmark results, and every score on this page links to its publisher.
- How does Mistral Large 2.1 rank?
- Mistral Large 2.1 is #590 of 785 ranked configurations on 25 Oct 2026. 285 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was Mistral Large 2.1 released?
- Mistral AI released Mistral Large 2.1 on 18 Nov 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Mistral Large 2.1: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/mistral-large-2-1.