Updated daily at 05:00 UTC
- Released
- 28 Apr 2026
- Status
- Current
- Context
- 262.1K
- Max output
- —
- Input per 1M tokens
- $1.50
- Output per 1M tokens
- $7.50
- Open weights
- Yes
- License
- modified-mit
- Parameters
- 128B
- Knowledge cutoff
- —
- Reasoning
- Yes
- Modalities
- image, text → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 30.7 | Not ranked | 1 of 4 |
| Coding & software engineering | 8.0 | Not ranked | 1 of 5 |
| Human preference | 42.5 | Not ranked | 2 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 75.5% | Third party | — | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.2606 | Third party | — | — | https://conceptualreasoning.ai/lmca via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Surface Evolver Bench | Mean score (partial credit) | 26.9% | Third party | — | — | https://yhenon.github.io/surface-evolver-llm-eval/ via Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierCode | Main score (Mean@5) | 8.0% | Third party | — | — | https://cognition.com/frontiercode via Epoch AI |
| WeirdML (v2) | Average accuracy | 43.7% | Third party | — | — | https://htihle.github.io/weirdml.html via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1263 | Independent | — | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 2322 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1426 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 11693 | Independent | — | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1200 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 5391 | Independent | — | 28 Sep 2026 | Arena |
Other Mistral Medium versions
- Mistral Medium 3.112 Aug 2025
- Mistral Medium 37 May 2025
- Mistral Medium 1.011 Dec 2023