Magistral Medium 1
Magistral Medium 1 is behind the leaders in factuality and agentic tasks. Too few results yet to rate reasoning, coding, safety, long context, math, multimodal tasks, multilingual tasks, or instruction following.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Coding, Safety, Long Context, Math, Multimodal, Multilingual or Instruction Following.
Price
No current price is tracked for this model. See the rate card
Evidence
24results on22benchmarks
- 2 independently verified
- 15 aggregator
- 7 vendor-reported
From 5 sources · latest Oct 8, 2026 · How verification works
Magistral Medium 1 benchmark results
24 results on 22 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
31.1% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination40.67Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy20.33Oct 8, 2026omniscienceAccuracy
42.3% behind the leader1 of 7 ranked benchmarks measured
- 8.26Jun 15, 2026
0 of 6 ranked benchmarks measured
- 0.00Aug 3, 2026
- 0.29Oct 8, 2026
- GPQA Diamond67.88Oct 8, 2026gpqa
Show 3 more reasoning resultsHide 3 reasoning results
- GPQA Diamond70.80Oct 7, 2026GPQA
- Humanity's Last Exam9.82Oct 8, 2026aa_hle
- 9.00Oct 7, 2026
0 of 10 ranked benchmarks measured
- Terminal-Bench Hard9.09Oct 8, 2026aa_terminalbench_hard
- SciCode29.69Sep 4, 2026aa_scicode
0 of 3 ranked benchmarks measured
- 0.00Oct 8, 2026
0 of 3 ranked benchmarks measured
- IFBench25.10Oct 8, 2026aa_ifbench
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- 6.12Aug 3, 2026
- -26.93Oct 8, 2026
- τ²-Bench Telecom (AA run)23.10Oct 8, 2026aa_tau2
- AA Intelligence9.05Oct 8, 2026aa_intelligence_index
- 15.96Jun 18, 2026
- 15.73Jun 18, 2026
Show 5 more resultsHide 5 results
- 47.10Oct 7, 2026
- 70.70Aug 3, 2026
- 64.90Oct 7, 2026
- 83.30Aug 3, 2026
- 50.30Aug 23, 2026
Magistral Medium 1: common questions
Who makes Magistral Medium 1?
Magistral Medium 1 is made by Mistral.
When was Magistral Medium 1 released?
Magistral Medium 1 was released on Jun 10, 2025, according to Artificial Analysis.
What is Magistral Medium 1 good at?
Magistral Medium 1 is behind the leaders in factuality and agentic tasks. Too few results yet to rate reasoning, coding, safety, long context, math, multimodal tasks, multilingual tasks, or instruction following.
How many benchmarks has Magistral Medium 1 been tested on?
We track 24 results for Magistral Medium 1 on 22 benchmarks from 5 sources, 2 of them independently verified. The latest was recorded on Oct 8, 2026.
About this record
Where Magistral Medium 1's numbers come from, and every name it appears under.
- Tracked since
- Apr 27, 2026
- Newest source mention
- Jun 4, 2026
Where the results come from
Verification: 24 scores · 2 independently verified · 15 aggregator-attributed · 7 vendor-reported. How these tiers are assigned
From 5 sources on 4 sites. Artificial Analysis supplies 15 of them; the 2 independently verified results come from 1 site. Bars are coloured by trust tier.
- artificialanalysis.ai15
- api.llm-stats.com5
- arcprize.org2
- mistral.ai2