whatmodel.sh / Magistral Medium 1.1 (2507)

Magistral Medium 1.1 (2507)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Magistral Medium 1.1 (2507) is a closed-weights language model from Mistral, released July 2025. Licence: proprietary.

Catalogue identity notes

Comparison-only. Mistral docs: 'July 24, 2025 Retired ... v 25.07 ... magistral-medium-2507 ... Context 40k ... Retirement date 11/30/2025'. API kept null (retired or deprecated in favour of Mistral Medium 3.5). Rows: Mistral's own Magistral-Small-2509 card table, row 'Magistral Medium 1.1'.

Model information sources

Release date ↗

55.2±1.5comparison only: no current run option verifiedfrom 4 benchmark results across 1 source

$ how it compares

The LLMs ranked either side of Magistral Medium 1.1 (2507), out of 828 with a score, then more from Mistral.

#modelscorewhereRAMreleased
313Qwen3 30B-A3B (Apr 2025, hybrid) Alibaba55±1api $0.35/M +local~19GB2025-04
314Molmo 2 8B Ai255±2local~6.8GB2025-12
315Magistral Medium 1.1 (2507) Mistral55±2comparison only2025-07
316Gemini 1.5 Pro Experimental (0801) Google55±1comparison only2024-08
317Qwen3 4B Instruct 2507 Alibaba55±1local~3.9GB2025-08
more from Mistral
79Mistral Large 4 (public preview) Mistral71±2api $2.06/M2026-10
174Mistral Medium 3.5 (128B) Mistral65±1api $3.00/M +local~42GB2026-04
180Mistral Medium 3.1 (2508) Mistral64±2comparison only2025-08

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▃█······▃·▃▃ #5 of 7 * · 11% of its score · 1 test

Beats Magistral Small 1.0 (2506) here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
LiveCodeBench v5 (window unspecified) lab59.4% ✎▄█▄······▄·▄ beats 2/5medium · avg 50%▇▇▇▇ 11%at its level
math▁▂▃▅▇▅▅█▄▁▁▁ #226 of 462 * · 58% 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, OpenThinker2 7B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AIME 2025 lab61.0% ✎█▃·····▃···▃ beats 0/5medium · avg 49%▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%sharp · at its level
AIME 2024 lab72.0% ✎█▃·····▃···▃ beats 2/5medium · avg 60%▇▇▇▇▇▇▇▇▇▇ 26%sharp · at its level
other tests1 not in a task · 30% of its score
testresultvs the others in its rundifficultycountswhy
GPQA Diamond lab71.5% ✎█·█·███····█ beats 4/5medium · avg 53%▇▇▇▇▇▇▇▇▇▇▇▇ 30%sharp · at its level

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · mistralai/Magistral-Small-250… 99%

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

sourceresultsshare of the scorelicence
mistralai/Magistral-Small-2509 model card · lab-reported4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 55.2

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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