Mistral AIDevstral Small 2
Devstral Small 2 is a Mistral AI open-weights model, released 9 Dec 2025. Its best configuration ranks #683 of 785 on the BenchLeader Index at 39.5 ±4.6, in the lower half. The ± is the point: 250 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 agents & tools (42) and lowest in multimodal (27). Last measured 1 Sept 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 256k
- Full answer
- –
- Cost per run
- –
- Released
- 9 Dec 2025
- Overall index40
- Reasoning41
- Coding37
- Agents & tools42
- Knowledge36
- Instruction following35
- Multimodal27
- Long context38
- Composite38
Versions
Mistral AI has shipped 3 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 |
|---|---|---|---|
| Devstral Small 2this page | 9 Dec 2025 | 39.5 | #683 |
| Devstral Small 2507 | 10 Jul 2025 | 41.9 | #613 |
| Devstral Small 2505 | 21 May 2025 | 41.7 | #620 |
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 (AA)not in index | 53.2%#413 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 3.5%#595 | Artificial Analysis | |
| CritPt | 0.0%#315 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| SciCode | 28.8%#200 | SciCode | |
| SciCode (AA)not in index | 32.4%#205 | Artificial Analysis | |
| LiveCodeBench | 43.2%#119 | Vals AI | |
| SWE-bench Verified (bash only) | 56.4%#26 | SWE-bench | |
| SWE-bench Verified (any scaffold)not in index | 56.4%#33 | SWE-bench | |
| Terminal-Bench 4.0 (AA)not in index | 0.0%#152 | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 29.6%#155 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Terminal-Bench Hard | 16.7%#184 | Artificial Analysis | |
| τ²-Bench Telecom (AA)not in index | 23.4%#304 | Artificial Analysis | |
| τ³-Banking (AA) | 10.7%#140 | Artificial Analysis | |
| AutomationBenchnot in index | 3.1%#175 | Artificial Analysis | |
| GDP.pdf (AA)not in index | 1.0%#204 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-Omniscience | -57.7#447 | Artificial Analysis | |
| AA-Omniscience: accuracynot in index | 15.8%#403 | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 12.7%#371 | Artificial Analysis |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| IFBench | 31.2%#358 | Artificial Analysis |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMMU-Pro | 44.6%#254 | Artificial Analysis |
Long context
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA-LCR | 28.0%#400 | Artificial Analysis |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 7.5#468 | Artificial Analysis |
More from Mistral AI
See also
Questions people ask
- What are Devstral Small 2's benchmark scores?
- As of 25 Oct 2026, Devstral Small 2 scores 39.5 ±4.6 on the BenchLeader Index, strongest in agents & tools (42) and weakest in multimodal (27). That rests on 11 independent benchmark results, and every score on this page links to its publisher.
- How does Devstral Small 2 rank?
- Devstral Small 2 is #683 of 785 ranked configurations on 25 Oct 2026. 250 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 Devstral Small 2 released?
- Mistral AI released Devstral Small 2 on 9 Dec 2025.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Devstral Small 2: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/devstral-small-2.