Mistral AIMagistral Medium 1.2
As of 29 Oct 2026, Magistral Medium 1.2 by Mistral AI scores 43.8 on the BenchLeader Index (581 ranked configurations), with its best results in long context (51) and weakest in knowledge (33). Released 18 Sept 2025; 14 independent results so far.
Key facts (as of 29 Oct 2026)
- Magistral Medium 1.2 was released on 18 Sept 2025 (Mistral AI).
In detail. Magistral Medium 1.2 is a Mistral AI proprietary reasoning model, released 18 Sept 2025. Its best configuration ranks #460 of 581 on the BenchLeader Index at 43.8 ±6.7, in the lower half. The ± is the point: 238 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 long context (51) and lowest in knowledge (33). Last measured 13 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 128k
- Full answer
- –
- Cost per run
- –
- Released
- 18 Sept 2025
- Overall index44
- Coding49
- Agents & tools37
- Maths40
- Knowledge33
- Instruction following45
- Multimodal42
- Long context51
Versions
Mistral AI has shipped 2 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 |
|---|---|---|---|
| Magistral Medium 1.2this page | 18 Sept 2025 | 43.8 | #460 |
| Magistral Mediummedium | 10 Jun 2025 | 40.8 | #500 |
How its index has moved
10 Sept 2026 to 29 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 |
|---|---|---|
| GPQA Diamond (AA)not in index | 73.9%#264 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 10.3%#329 | Artificial Analysis |
| GPQA Diamond (Vals)not in index | 62.4%#103 | Vals AI |
| CritPtnot in index | 0.3%#283 | Artificial Analysis |
Coding
| Benchmark | not stated | Source |
|---|---|---|
| SciCode | 39.2%#177 | SciCode |
| LiveCodeBench | 74.9%#80 | Vals AI |
| Terminal-Bench 2.1 (AA)not in index | 12.4%#190 | Artificial Analysis |
| LiveCodeBench (AA)not in index | 75.0%#44 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source |
|---|---|---|
| Terminal-Bench Hard | 12.9%#208 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 52.0%#197 | Artificial Analysis |
| GDPval-AA v2.1, normalised scorenot in index | 0.0%#124 | Artificial Analysis |
| GDPval-AA v2.1not in index | 176#149 | Artificial Analysis |
| τ³-Banking (AA) | 5.6%#177 | Artificial Analysis |
| Terminal-Bench 2.0 (Vals)not in index | 13.5%#61 | Vals AI |
Maths
| Benchmark | not stated | Source |
|---|---|---|
| AIME (Vals) | 83.5%#42 | Vals AI |
| MGSM | 74.6%#68 | Vals AI |
| AIME 2025 (AA)not in index | 82.0%#14 | Artificial Analysis |
Knowledge
Instruction following
| Benchmark | not stated | Source |
|---|---|---|
| IFBench | 43.0%#232 | Artificial Analysis |
Multimodal
| Benchmark | not stated | Source |
|---|---|---|
| MMMU-Pro | 59.6%#221 | Artificial Analysis |
| MMMU-Pro (Vals)not in index | 64.6%#76 | Vals AI |
| MortgageTaxnot in index | 51.9%#80 | Vals AI |
Long context
| Benchmark | not stated | Source |
|---|---|---|
| AA-LCR v1.1 | 53.0%#319 | Artificial Analysis |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| AA Intelligence Index v4.3.2not in index | 11.8#352 | Artificial Analysis |
| AA Progress Index v1not in index | 221.1#340 | Artificial Analysis |
More from Mistral AI
See also
Questions people ask
- What are Magistral Medium 1.2's benchmark scores?
- As of 29 Oct 2026, Magistral Medium 1.2 scores 43.8 ±6.7 on the BenchLeader Index, strongest in long context (51) and weakest in knowledge (33). That rests on 14 independent benchmark results, and every score on this page links to its publisher.
- How does Magistral Medium 1.2 rank?
- Magistral Medium 1.2 is #460 of 581 ranked configurations on 29 Oct 2026. 238 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 69.1.
- When was Magistral Medium 1.2 released?
- Mistral AI released Magistral Medium 1.2 on 18 Sept 2025.
Data as of 29 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Magistral Medium 1.2: benchmarks, pricing, speed and rank”, data as of 29 Oct 2026, https://www.benchleader.com/models/magistral-medium-2509.