Mistral Small 3.1
Mistral Small 3.1 is behind the leaders in coding. Too few results yet to rate reasoning, agentic tasks, safety, long context, math, multimodal tasks, multilingual tasks, instruction following, or factuality.
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, Agentic, Safety, Long Context, Math, Multimodal, Multilingual, Instruction Following or Factuality.
Price
$0.11input$0.17outputper million tokens
From Artificial Analysis · All prices
Evidence
24results on21benchmarks
- 6 independently verified
- 18 aggregator
From 2 sources · latest Oct 8, 2026 · How verification works
Mistral Small 3.1 benchmark results
24 results on 21 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
44.5% behind the leader3 of 10 ranked benchmarks measured
- SciCode27.78Oct 8, 2026aa_scicode
- Terminal-Bench 2.126.22Oct 8, 2026terminalbenchV21
- Terminal-Bench Hard7.58Oct 8, 2026aa_terminalbench_hard
Show 2 more coding resultsHide 2 coding results
- LiveBench · Coding36.72Aug 23, 2026livebench_coding@2025-04-07
- LiveBench · Coding36.72Jun 17, 2026livebench_coding@2025-04-07
0 of 6 ranked benchmarks measured
- 0.00Oct 8, 2026
- GPQA Diamond45.35Oct 8, 2026gpqa
- Humanity's Last Exam4.31Oct 8, 2026aa_hle
0 of 7 ranked benchmarks measured
- 0.00Oct 8, 2026
- Terminal-Bench 4.00.00Oct 8, 2026
- τ-Bench V3 · Banking7.42Oct 8, 2026tauBanking
0 of 3 ranked benchmarks measured
- 22.33Oct 8, 2026
0 of 3 ranked benchmarks measured
- LiveBench · Instruction Following62.42Aug 23, 2026livebench_instruction_following@2025-04-07
- LiveBench · Instruction Following62.42Jun 17, 2026livebench_instruction_following@2025-04-07
- IFBench29.93Oct 8, 2026aa_ifbench
0 of 4 ranked benchmarks measured
- AA-Omniscience · Accuracy15.10Oct 8, 2026omniscienceAccuracy
- AA-Omniscience · Non-hallucination22.44Oct 8, 2026omniscienceNonHallucination
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- livebench_language33.77Aug 23, 2026livebench_language@2025-04-07
- livebench_language33.77Jun 17, 2026livebench_language@2025-04-07
- -50.75Oct 8, 2026
- AA Intelligence7.12Oct 8, 2026aa_intelligence_index
- τ²-Bench Telecom (AA run)25.15Oct 8, 2026aa_tau2
- 2.07Sep 9, 2026
Show 1 more resultHide 1 result
- Artificial Analysis Coding Index26.31Sep 9, 2026aa_coding_index
Mistral Small 3.1: common questions
Who makes Mistral Small 3.1?
Mistral Small 3.1 is made by Mistral.
When was Mistral Small 3.1 released?
Mistral Small 3.1 was released on Mar 17, 2025, according to Artificial Analysis.
What is Mistral Small 3.1 good at?
Mistral Small 3.1 is behind the leaders in coding. Too few results yet to rate reasoning, agentic tasks, safety, long context, math, multimodal tasks, multilingual tasks, instruction following, or factuality.
How much does Mistral Small 3.1 cost?
Mistral Small 3.1 costs $0.11 per million input tokens and $0.17 per million output tokens, according to Artificial Analysis. At a mix of three input tokens to one output token, it is cheaper than 87% of the 331 priced models we track.
How many benchmarks has Mistral Small 3.1 been tested on?
We track 24 results for Mistral Small 3.1 on 21 benchmarks from 2 sources, 6 of them independently verified. The latest was recorded on Oct 8, 2026.
About this record
Where Mistral Small 3.1's numbers come from, and every name it appears under.
- Tracked since
- Apr 27, 2026
- Newest source mention
- Jun 26, 2026
Where the results come from
Verification: 24 scores · 6 independently verified · 18 aggregator-attributed. How these tiers are assigned
From 2 sources on 2 sites. Artificial Analysis supplies 18 of them; the 6 independently verified results come from 1 site. Bars are coloured by trust tier.
- artificialanalysis.ai18
- huggingface.co6