Devstral Medium
Devstral Medium 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
$0.40input$2.00outputper million tokens
From mistralai · All prices
Evidence
17results on17benchmarks
- 1 independently verified
- 15 aggregator
- 1 vendor-reported
From 3 sources · latest Oct 8, 2026 · How verification works
API features
Tool callingStructured outputs
As listed by OpenRouter
Devstral Medium benchmark results
17 results on 17 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
33.2% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination37.81Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy18.88Oct 8, 2026omniscienceAccuracy
42.0% behind the leader1 of 7 ranked benchmarks measured
- 9.56Jun 15, 2026
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond49.19Oct 8, 2026gpqa
- Humanity's Last Exam3.75Oct 8, 2026aa_hle
0 of 10 ranked benchmarks measured
- 1078.91May 22, 2026
- Terminal-Bench Hard9.09Oct 8, 2026aa_terminalbench_hard
- SciCode29.40Sep 4, 2026aa_scicode
Show 1 more coding resultHide 1 coding result
- 61.60Oct 7, 2026
0 of 3 ranked benchmarks measured
- 32.00Oct 8, 2026
0 of 3 ranked benchmarks measured
- IFBench29.93Oct 8, 2026aa_ifbench
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- τ²-Bench Telecom (AA run)19.88Oct 8, 2026aa_tau2
- AA Intelligence9.01Oct 8, 2026aa_intelligence_index
- -31.57Oct 8, 2026
- 15.86Jun 18, 2026
- 15.84Jun 18, 2026
Devstral Medium: common questions
Who makes Devstral Medium?
Devstral Medium is made by Mistral.
When was Devstral Medium released?
Devstral Medium was released on Jul 10, 2025, according to Artificial Analysis.
What is Devstral Medium good at?
Devstral Medium 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 much does Devstral Medium cost?
Devstral Medium costs $0.40 per million input tokens and $2.00 per million output tokens, according to mistralai. At a mix of three input tokens to one output token, it costs more than 52% of the 330 priced models we track.
How many benchmarks has Devstral Medium been tested on?
We track 17 results for Devstral Medium on 17 benchmarks from 3 sources, 1 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does Devstral Medium support?
OpenRouter lists tool calling and structured outputs for Devstral Medium.
About this record
Where Devstral Medium's numbers come from, and every name it appears under.
- Tracked since
- May 2, 2026
- Newest source mention
- Aug 3, 2026
Where the results come from
Verification: 17 scores · 1 independently verified · 15 aggregator-attributed · 1 vendor-reported. How these tiers are assigned
From 3 sources on 3 sites. Artificial Analysis supplies 15 of them; the 1 independently verified result comes from 1 site. Bars are coloured by trust tier.
- artificialanalysis.ai15
- api.llm-stats.com1
- datasets-server.huggingface.co1