Magistral Medium 1.2
Sep 2025
Retired 2026-07-31Replace withMistral Medium 3.5Newer version
GPT-6 LunaBetter
MiMo v2.6 ProOpen weights
Mistral Medium 3.5Newer versionGPT-6 LunaBetterMiMo v2.6 ProOpen weightsMagistral Medium 1.2Compare inon
Benchmarks of Magistral Medium 1.218
BenchmarkByScoreRank
Overall1
Knowledge4
Science2
Coding1
Agents2
Multimodal1
Health & law1
Documents1
Legacy · saturated or no longer reported5
No benchmark matches
—per task?
not available via APIprice
—output speed?
128Kcontext
Rankingin thinking mode?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-6 Lunalow+82%—$0.005Function calling only with none · Chat Completions+3OpenMiMo v2.6 Prothinking×3.9—$0.13Pass back reasoning_content+3BetterGPT-5.6 Lunalow+78%—$0.01BetterMiMo v2.5thinkingOpen+85%—$0.019
BetterClaude Haiku 5.5low×2.5—$0.024Remove sampling parameters+5ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-6 Lunalow+82%—$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+78%—$0.01MiMo v2.5thinkingOpen+85%—$0.019Claude Haiku 5.5low×2.5—$0.024Remove sampling parameters+5GPT-5 Minihigh+42%—$0.053ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×3.9—$0.13Pass back reasoning_content+3
DeepSeek V4.1 Flash 1017maxOpen×3.8—$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen×3.8—$2.01No image input+4
Step 5 PreviewthinkingOpen×3.7—$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen×3.7—$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
Mistral Large 4thinking×3.2—$1.13Infinite whitespace stream+4Mistral Medium 3.5highOpen+20%—$0.50Mistral Small 4thinkingOpensame—$0.015Mistral Large 3non-thinkingOpen-22%—$0.031Magistral Medium 1thinking-23%——Context: 128K → 40K+1Devstral Mediumnon-thinkingOpen-24%—$0.40 / $2No image inputMagistral Small 1thinkingOpen-30%—$0.70 / $1.16No image inputMistral Small 3non-thinkingOpen-44%—$0.05 / $0.08Context: 128K → 32K+1All Mistral models →History
2 versionsBenchmarks
all categoriesChat & Knowledge
AA Omniscience Index-26.7
GPQA Diamond73.9
Coding
Agents & Tool Use
Writing & Language
Vision & Documents
FAQ
How much does Magistral Medium 1.2 cost?›
There is no per-unit API price: not available via API.
Is Magistral Medium 1.2 free to use?›
There is no free API.
What is the context window of Magistral Medium 1.2?›
128K tokens.
When was Magistral Medium 1.2 released? Is there a newer version?›
Released 2025-09-18. It has been superseded by Mistral Medium 3.5.
Is Magistral Medium 1.2 open source?›
No, Magistral Medium 1.2 is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can Magistral Medium 1.2 read images?›
It accepts text and images as input.
What is Magistral Medium 1.2?›
Magistral Medium 1.2 is a closed language model from Mistral, released Sep 2025, the successor to Magistral Medium 1.
What are the best alternatives to Magistral Medium 1.2?›
GPT-6 Luna (better), MiMo v2.6 Pro (open weights).