whatmodel.sh / Magistral Medium 1.0 (2506)
Magistral Medium 1.0 (2506)
↗ share
+ contribute
Magistral Medium 1.0 (2506) is a closed-weights language model from Mistral, released June 2025.
Catalogue identity notes
Comparison-only. Arena entry 'magistral-medium-2506' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'magistral-medium-2506' as 'magistral-medium-2506' (Mistral, Proprietary), linking https://mistral.ai/news/magistral. Released 2025-06: Mistral model card: 'released June 2025'. Mistral card: retired 11/30/2025.
$ how it compares
The LLMs ranked either side of Magistral Medium 1.0 (2506), out of 828 with a score, then more from Mistral.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 304 | Ministral 3 14B | 56±1 | api $0.20/M +local | ||
| 305 |  Nemotron Nano 9B v2 | 56±1 | api $0.10/M +local | ||
| 306 | Magistral Medium 1.0 (2506) | 56±1 | comparison only | ||
| 307 |  GPT-4 Turbo (2024-04-09) | 55±0 | api $15.00/M | ||
| 308 |  Yi-Lightning | 55±1 | api price unknown | ||
| more from Mistral | |||||
| 79 | Mistral Large 4 (public preview) | 71±2 | api $2.06/M | ||
| 174 | Mistral Medium 3.5 (128B) | 65±1 | api $3.00/M +local | ||
| 180 | Mistral Medium 3.1 (2508) | 64±2 | comparison only | ||
$ what it's good at
agent tasks▁▁▂▆█▆▅▄▄▃▂▁ #232 of 340 * · 3.0% of its score · 1 test
Beats o1 (2024-12-17), o3-mini, DeepSeek R1 (Jan '25) here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Mellum2 12B-A2.5B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Galileo Agent Leaderboard v2 (action completion) | 32.0% ✎ | ▅▃·▃▃▅▅█▃█▅▅ beats 5/19 | 3.0% |
coding▃█······▃·▃▃ #4 of 7 * · 8.7% of its score · 1 test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LiveCodeBench v5 (window unspecified) lab | 59.4% ✎ | ▄█▄······▄·▄ beats 3/5 | 8.7% |
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #257 of 463 * · 16% of its score · 1 test
Beats Granite 4.2 8B, Mistral Small 4 (119B-A6.5B), Olmo 3.1 32B Think here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, Olmo 3 7B Instruct, Granite 4.0 H Micro 3B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1304.8 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 132/379 | 16% |
math▁▂▃▅▇▅▅█▄▁▁▁ #216 of 462 * · 47% of its score · 2 tests
Beats MiniMax-M2.1, Qwen3 235B-A22B (Apr 2025, hybrid), DeepSeek V3 (Dec '24) here, though they rank higher overall. Trails Phi-4-mini-reasoning 3.8B, DeepSeek R1 Distill Qwen 7B, OpenThinker3 7B here, though they rank lower overall.
other tests1 not in a task · 25% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GPQA Diamond lab | 70.8% ✎ | █·█·███····█ beats 3/5 | 25% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · mistralai/Magistral-Small-250… 80%, LMArena leaderboard dataset 16%, Galileo Agent Leaderboard (v1… 3%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 mistralai/Magistral-Small-2509 model card · lab-reported | 4 | 80% |
 LMArena leaderboard dataset | 1 | 16% |
| Galileo Agent Leaderboard (v1 and v2 results) | 1 | 3% |
| prior · pull toward the middle | 1% | |
| weighted average | = 55.5 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json