Magistral Medium 1
Jun 2025
Magistral Medium 1Compare inon
Benchmarks of Magistral Medium 116
BenchmarkByScoreRank
Overall1
Knowledge4
Reasoning4
Science2
Coding1
Legacy · saturated or no longer reported4
No benchmark matches
—per task?
not available via APIprice
—output speed?
40Kcontext
Rankingin thinking mode?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow×2—$0.005Function calling only with none · Chat Completions+3
OpenDeepSeek V4 Pro 0813max×2.4—$0.67Pass back reasoning_content · Chat Completions+4BetterGPT-5.6 Lunalow+95%—$0.01BetterDeepSeek V3non-thinkingOpen+25%—$0.02BetterDeepSeek V3 0324non-thinkingOpen+20%—$0.021ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow×2—$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+95%—$0.01DeepSeek V3non-thinkingOpen+25%—$0.02DeepSeek V3 0324non-thinkingOpen+20%—$0.021
Claude Haiku 5.5low+64%—$0.024Remove sampling parameters+5ModelScoreCostPer taskWhat changes
DeepSeek V4 Pro 0813maxOpen×2.4—$0.67Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpen×2.3—$2.00Sampling parameters are fixed+3DeepSeek V4.1 Flash 1017maxOpen×2.1—$0.26Pass back reasoning_content · Chat Completions+4TInklingxhighOpen×2—$0.95 / $4.05
Step 5 PreviewthinkingOpen×2—$1.03web_search not available · Chat Completions+2ModelScoreCostPer taskWhat changes
Mistral Large 4thinking+27%—$1.13Infinite whitespace stream+4Mistral Large 3non-thinkingOpen+23%—$0.031Mistral Medium 3.5highOpen+21%—$0.50Mistral Small 4thinkingOpen+7%—$0.015Devstral Mediumnon-thinkingOpen-7%—$0.40 / $2Magistral Small 1thinkingOpen-11%—$0.70 / $1.16Ministral 3 14B 2512non-thinkingOpen-33%—$0.019Ministral 3 8B 2512Open-36%—$0.011All Mistral models →History
2 versionsBenchmarks
all categoriesChat & Knowledge
Humanity's Last Exam9.8#196
AA Omniscience Index-26.9#141
CritPt (physics)0.3#149
AA Intelligence Index 4.3.2≈9.1#228
AA Omniscience · Accuracy20.3#151
GPQA Diamond67.9#198
AIME 2025 · AA archived40.3#96
Coding
LiveCodeBench · AA archived52.7#82
Agents & Tool Use
τ²-bench · AA23.1#179
Writing & Language
IFBench (instructions)25.1#232
FAQ
How much does Magistral Medium 1 cost?›
There is no per-unit API price: not available via API.
Is Magistral Medium 1 free to use?›
There is no free API.
How good is Magistral Medium 1, and what is it best at?›
#195 of 334 in Chat & Knowledge, #128 of 239 in Coding, #177 of 242 in Agents & Tool Use, #229 of 245 in Writing & Language.
Is Magistral Medium 1 better than Ling 1T?›
On AA Omniscience · Accuracy, Magistral Medium 1 scores 20.3 vs 20.3 — about the same.
What is the context window of Magistral Medium 1?›
40K tokens.
When was Magistral Medium 1 released? Is there a newer version?›
Released 2025-06-10. It has been superseded by Magistral Medium 1.2.
Is Magistral Medium 1 open source?›
No, Magistral Medium 1 is a closed model available through an API. The closest open-weights option here is DeepSeek V4 Pro 0813.
Can Magistral Medium 1 read images?›
No, it accepts text only.
What is Magistral Medium 1?›
Magistral Medium 1 is a closed language model from Mistral, released Jun 2025.
What are the best alternatives to Magistral Medium 1?›
GPT-6 Luna (better), DeepSeek V4 Pro 0813 (open weights).