Mistral AIMistral Small 3.1
Mistral Small 3.1 is a Mistral AI open-weights model, released 17 Mar 2025. Its best configuration ranks #749 of 785 on the BenchLeader Index at 36.3 ±3.2, in the lower half. The ± is the point: 145 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 (39) and lowest in coding (21). At $0.095 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 41 tokens per second puts it in the slowest quarter, with a first answer in 0.9 s. Last measured 13 Oct 2026.
- Blended price
- $0.095/M
- $0.080 in · $0.140 out
- Output speed
- 41 tok/s
- measured by Artificial Analysis
- First answer
- 0.89 s
- first token 0.89 s
- Context
- 128k
- Full answer
- 13 s
- median, reasoning included
- Cost per run
- $0.026
- one full Intelligence Index run
- Released
- 17 Mar 2025
- Overall index36
- Reasoning39
- Coding21
- Agents & tools37
- Maths35
- Knowledge33
- Instruction following39
- Long context35
- Composite37
Versions
Mistral AI has shipped 6 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 Small 4thinking | 16 Mar 2026 | 45.6 | #511 |
| Mistral Small 3.2 | 20 Jun 2025 | 41.6 | #622 |
| Mistral Small 3.1this page | 17 Mar 2025 | 36.3 | #749 |
| Mistral Small 3 | 25 Jan 2025 | 39.3 | #688 |
| Mistral Small v24.09 | 17 Sept 2024 | – | – |
| Mistral Small 2402 | 26 Feb 2024 | 32.0 | #781 |
How its index has moved
9 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 | 47.5%#225 | Epoch AI Benchmarking Hub | |
| GPQA Diamond (AA)not in index | 45.4%#451 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 4.3%#510 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | 44.2%#122 | Vals AI | |
| GPQA Diamond (HELM)not in index | 39.2%#49 | HELM Capabilities | |
| CritPt | 0.0%#315 | Artificial Analysis | |
| DTBenchnot in index | 58.6%#191 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode | 27.8%#202 | SciCode | |
| SciCode (AA)not in index | 27.8%#215 | Artificial Analysis | |
| LiveCodeBench | 31.8%#132 | Vals AI | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 26.2%#165 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 7.6%#241 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 25.1%#294 | Artificial Analysis | |
| τ³-Banking (AA) | 7.4%#161 | Artificial Analysis | |
| AutomationBenchnot in index | 1.2%#192 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 1.0%#204 | Artificial Analysis |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 5.8%#244 | Epoch AI Benchmarking Hub | |
| MATH Level 5 | 46.8%#55 | Epoch AI Benchmarking Hub | |
| AIME (Vals) | 3.5%#89 | Vals AI | |
| MGSM | 84.2%#66 | Vals AI | |
| Omni-MATH (HELM) | 24.8%#51 | HELM Capabilities | |
| MATH 500not in index | 68.4%#52 | Vals AI |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -50.8#394 | Artificial Analysis | |
| MMLU-Pro | 66.0%#121 | Vals AI | |
| LegalBench | 69.2%#122 | Vals AI | |
| CorpFin | 44.2%#111 | Vals AI | |
| TaxEval | 58.3%#128 | Vals AI | |
| MedQA | 69.1%#78 | Vals AI | |
| MMLU-Pro (HELM)not in index | 61.0%#45 | HELM Capabilities | |
| AA-Omniscience: accuracynot in index | 15.1%#422 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 22.4%#264 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 29.9%#365 | Artificial Analysis | |
| IFEval (HELM) | 75.0%#57 | HELM Capabilities | |
| WildBench (HELM) | 78.8%#42 | HELM Capabilities |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMMU-Pro (Vals)not in index | 60.1%#81 | Vals AI | |
| MortgageTaxnot in index | 61.2%#60 | Vals AI |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 22.3%#422 | Artificial Analysis | |
| MLCRnot in index | 2.2%#158 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 127.5#154 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 7.1#492 | Artificial Analysis | |
| HELM Capabilities meannot in index | 55.8%#52 | HELM Capabilities |
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 | $0.0001 | – | 8.2 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0010 | – | 15.5 s |
| Code edit | 6,000 / 1,500 | $0.0007 | – | 37.4 s |
| Agentic coding session | 60,000 / 4,000 | $0.0054 | – | 1.6 min |
| Structured extraction | 2,000 / 200 | $0.0002 | – | 5.8 s |
More from Mistral AI
See also
Questions people ask
- What are Mistral Small 3.1's benchmark scores?
- As of 24 Oct 2026, Mistral Small 3.1 scores 36.3 ±3.2 on the BenchLeader Index, strongest in instruction following (39) and weakest in coding (21). That rests on 22 independent benchmark results, and every score on this page links to its publisher.
- How does Mistral Small 3.1 rank?
- Mistral Small 3.1 is #749 of 785 ranked configurations on 24 Oct 2026. 145 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 Small 3.1 cost per 1M tokens?
- As of 24 Oct 2026, Mistral Small 3.1 costs $0.080 per 1M input tokens and $0.140 per 1M output tokens, $0.095 blended (three input tokens per output token). The list price last changed on 13 Oct 2026.
- When was Mistral Small 3.1 released?
- Mistral AI released Mistral Small 3.1 on 17 Mar 2025.
Data as of 24 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Mistral Small 3.1: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/mistral-small-3-1.