Mistral AIMistral Large 2
Mistral Large 2 is a Mistral AI open-weights model, released 24 Jul 2024. Its best configuration ranks #652 of 785 on the BenchLeader Index at 40.7 ±4.8, in the lower half. The ± is the point: 283 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 human preference (47) and lowest in long context (25). At $3.00 per million tokens blended it is pricier than most ranked models. Output speed of 51 tokens per second puts it in the slowest quarter, with a first token in 0.6 s. Last measured 22 Oct 2026.
- Blended price
- $3.00/M
- $2.00 in · $6.00 out
- Output speed
- 51 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 0.64 s
- Context
- 131k
- Full answer
- –
- Cost per run
- –
- Released
- 24 Jul 2024
- Overall index41
- Reasoning36
- Coding47
- Maths41
- Instruction following35
- Human preference47
- Long context25
- Composite37
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 2.1 | 18 Nov 2024 | 42.5 | #590 |
| Mistral Large 2this page | 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 21 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 | 49.0%#219 | Epoch AI Benchmarking Hub | |
| SimpleBench | 22.5%#79 | SimpleBench | |
| Arena Hard Prompts | 1320#242 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 47.2%#442 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 3.0%#606 | Artificial Analysis | |
| DTBenchnot in index | 61.2%#183 | Epoch AI Benchmarking Hub | |
| ForecastBenchnot in index | 61.7%#62 | ForecastBench |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Coding | 1354#240 | Arena (LMArena) |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| τ²-Bench Telecom (AA)not in index | 33.0%#245 | Artificial Analysis |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 8.5%#230 | Epoch AI Benchmarking Hub | |
| MATH Level 5 | 44.8%#58 | Epoch AI Benchmarking Hub | |
| Arena Maths | 1288#238 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMLUnot in index | 80.0%#20 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 31.6%#349 | Artificial Analysis | |
| Arena Instruction Followingnot in index | 1299#238 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1314#242 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1287#231 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1297#243 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1305#253 | Arena (LMArena) | |
| Lech Mazur Creative Writingnot in index | 69.0%#34 | Lech Mazur |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 2.0%#491 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 127.6#153 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 6.8#507 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Mistral | 55 tok/s | 0.56 s | $2.00 | $6.00 | 131k | – |
| Mistral | 55 tok/s | 0.74 s | $2.00 | $6.00 | 131k | – |
Price history
The price above, per 1M tokens, every day it changed.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0026 | – | 6.5 s |
| Summarize a 30-page report | 12,000 / 600 | $0.028 | – | 12.4 s |
| Code edit | 6,000 / 1,500 | $0.021 | – | 30.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.144 | – | 1.3 min |
| Structured extraction | 2,000 / 200 | $0.0052 | – | 4.6 s |
More from Mistral AI
See also
Questions people ask
- What are Mistral Large 2's benchmark scores?
- As of 25 Oct 2026, Mistral Large 2 scores 40.7 ±4.8 on the BenchLeader Index, strongest in human preference (47) and weakest in long context (25). That rests on 11 independent benchmark results, and every score on this page links to its publisher.
- How does Mistral Large 2 rank?
- Mistral Large 2 is #652 of 785 ranked configurations on 25 Oct 2026. 283 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.
- How much does Mistral Large 2 cost per 1M tokens?
- As of 25 Oct 2026, Mistral Large 2 costs $2.00 per 1M input tokens and $6.00 per 1M output tokens, $3.00 blended (three input tokens per output token). The list price last changed on 9 Sept 2026.
- When was Mistral Large 2 released?
- Mistral AI released Mistral Large 2 on 24 Jul 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Mistral Large 2: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/mistral-large-2.