Mistral AIMistral Medium 3.1
Mistral Medium 3.1 is a Mistral AI proprietary model, released 12 Aug 2025. Its best configuration ranks #494 of 785 on the BenchLeader Index at 46.1 ±4.5, in the lower half. The ± is the point: 308 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 (58) and lowest in agents & tools (38). At $0.800 per million tokens blended it is mid-priced. Output speed of 79 tokens per second puts it slower than most, with a first token in 0.6 s. Last measured 22 Oct 2026.
- Blended price
- $0.800/M
- $0.400 in · $2.00 out
- Output speed
- 79 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 0.60 s
- Context
- 262k
- Full answer
- –
- Cost per run
- –
- Released
- 12 Aug 2025
- Overall index46
- Reasoning47
- Coding42
- Agents & tools38
- Maths57
- Knowledge41
- Instruction following43
- Human preference58
- Multimodal42
- Long context46
- Composite40
Versions
Mistral AI has shipped 4 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 Medium 3.5 | 28 Apr 2026 | 49.4 | #397 |
| Mistral Medium 3.1this page | 12 Aug 2025 | 46.1 | #494 |
| Mistral Medium 3 | 7 May 2025 | 44.1 | #546 |
| Mistral Medium 2312 | 11 Dec 2023 | – | – |
How its index has moved
9 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 |
|---|---|---|---|
| Arena Hard Prompts | 1427#140 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 58.8%#384 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 4.7%#480 | Artificial Analysis | |
| CritPt | 0.0%#315 | Artificial Analysis | |
| LMCAnot in index | 19.1%#160 | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 67.5%#164 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode | 32.4%#195 | SciCode | |
| WeirdML | 33.1%#131 | WeirdML | |
| Arena Coding | 1453#142 | Arena (LMArena) | |
| SciCode (AA)not in index | 32.4%#205 | Artificial Analysis | |
| ALE-Benchnot in index | 210.2#124 | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 13.9%#184 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 10.6%#221 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 40.6%#222 | Artificial Analysis | |
| τ³-Banking (AA) | 8.3%#157 | Artificial Analysis | |
| AutomationBenchnot in index | 4.2%#170 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 1.2%#198 | Artificial Analysis |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Maths | 1395#155 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -46.3#357 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 20.8%#294 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 15.4%#334 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 39.8%#263 | Artificial Analysis | |
| Arena Instruction Followingnot in index | 1395#144 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1408#143 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1378#137 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1407#145 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1408#147 | Arena (LMArena) |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Vision | 1172#106 | Arena (LMArena) | |
| MMMU-Pro | 54.2%#230 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 42.7%#348 | Artificial Analysis | |
| MLCRnot in index | 2.8%#158 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 9.2#407 | 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 | 75 tok/s | 0.56 s | $0.400 | $2.00 | 131k | – |
| Mistral | 70 tok/s | 0.29 s | $0.400 | $2.00 | 131k | – |
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 | $0.0008 | – | 4.4 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0060 | – | 8.2 s |
| Code edit | 6,000 / 1,500 | $0.0054 | – | 19.6 s |
| Agentic coding session | 60,000 / 4,000 | $0.032 | – | 51.2 s |
| Structured extraction | 2,000 / 200 | $0.0012 | – | 3.1 s |
More from Mistral AI
See also
Questions people ask
- What are Mistral Medium 3.1's benchmark scores?
- As of 25 Oct 2026, Mistral Medium 3.1 scores 46.1 ±4.5 on the BenchLeader Index, strongest in human preference (58) and weakest in agents & tools (38). That rests on 15 independent benchmark results, and every score on this page links to its publisher.
- How does Mistral Medium 3.1 rank?
- Mistral Medium 3.1 is #494 of 785 ranked configurations on 25 Oct 2026. 308 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 Medium 3.1 cost per 1M tokens?
- As of 25 Oct 2026, Mistral Medium 3.1 costs $0.400 per 1M input tokens and $2.00 per 1M output tokens, $0.800 blended (three input tokens per output token).
- When was Mistral Medium 3.1 released?
- Mistral AI released Mistral Medium 3.1 on 12 Aug 2025.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Mistral Medium 3.1: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/mistral-medium-3-1.