Mistral Large 2
Mistral Large 2 is behind the leaders in factuality. Too few results yet to rate reasoning, coding, agentic tasks, 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, Agentic, Safety, Long Context, Math, Multimodal, Multilingual or Instruction Following.
Price
$2.00input$6.00outputper million tokens
From Artificial Analysis · 2 providers tracked · All prices
Evidence
39results on28benchmarks
- 14 independently verified
- 22 aggregator
- 3 vendor-reported
From 11 sources · latest Oct 8, 2026 · How verification works
API features
Tool callingStructured outputs
As listed by OpenRouter
Mistral Large 2 benchmark results
39 results on 28 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
33.3% behind the leader2 of 4 ranked benchmarks measured
- AA-Omniscience · Non-hallucination32.32Oct 8, 2026omniscienceNonHallucination
- AA-Omniscience · Accuracy19.87Oct 8, 2026omniscienceAccuracy
0 of 6 ranked benchmarks measured
- 22.50May 10, 2026
- 0.00Oct 8, 2026
- GPQA Diamond48.59Oct 8, 2026gpqa
Show 3 more reasoning resultsHide 3 reasoning results
- GPQA Diamond47.17Oct 8, 2026gpqa
- Humanity's Last Exam3.34Oct 8, 2026aa_hle
- Humanity's Last Exam2.95Oct 8, 2026aa_hle
0 of 10 ranked benchmarks measured
- LiveBench · Coding46.88Aug 23, 2026livebench_coding@2025-04-07
- LiveBench · Coding46.88Jun 17, 2026livebench_coding@2025-04-07
- Terminal-Bench Hard6.06Oct 8, 2026aa_terminalbench_hard
0 of 7 ranked benchmarks measured
- 0.00Jun 15, 2026
0 of 3 ranked benchmarks measured
- 2.00Oct 8, 2026
- 5.33Sep 4, 2026
0 of 3 ranked benchmarks measured
- LiveBench · Instruction Following66.33Aug 23, 2026livebench_instruction_following@2025-04-07
- LiveBench · Instruction Following66.78Jun 17, 2026livebench_instruction_following@2025-04-07
- IFBench31.22Oct 8, 2026aa_ifbench
Show 1 more instruction following resultHide 1 instruction following result
- IFBench31.63Oct 8, 2026aa_ifbench
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- livebench_language36.81Aug 23, 2026livebench_language@2025-04-07
- 93.20Jul 2, 2026
- 91.20Jul 2, 2026
- livebench_language36.81Jun 17, 2026livebench_language@2025-04-07
- 35.26May 19, 2026
- 45.27May 10, 2026
Show 13 more resultsHide 13 results
- 10.23Jun 18, 2026
- AA Intelligence7.56Oct 8, 2026aa_intelligence_index
- AA Intelligence6.80Oct 8, 2026aa_intelligence_index
- -34.37Oct 8, 2026
- 13.76Jun 18, 2026
- 93.00Oct 7, 2026
- 92.00Oct 7, 2026
- 67.67May 10, 2026
- 72.46May 10, 2026
- 8.63Oct 7, 2026
- 77.87May 10, 2026
- τ²-Bench Telecom (AA run)30.70Oct 8, 2026aa_tau2
- τ²-Bench Telecom (AA run)33.04Oct 8, 2026aa_tau2
Mistral Large 2: common questions
Who makes Mistral Large 2?
Mistral Large 2 is made by Mistral.
When was Mistral Large 2 released?
Mistral Large 2 was released on Nov 18, 2024, according to Artificial Analysis.
What is Mistral Large 2 good at?
Mistral Large 2 is behind the leaders in factuality. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multimodal tasks, multilingual tasks, or instruction following.
How much does Mistral Large 2 cost?
Mistral Large 2 costs $2.00 per million input tokens and $6.00 per million output tokens, according to Artificial Analysis. We track its price at 2 providers. At a mix of three input tokens to one output token, it costs more than 75% of the 331 priced models we track.
How many benchmarks has Mistral Large 2 been tested on?
We track 39 results for Mistral Large 2 on 28 benchmarks from 11 sources, 14 of them independently verified. The latest was recorded on Oct 8, 2026.
Which API features does Mistral Large 2 support?
OpenRouter lists tool calling and structured outputs for Mistral Large 2.
About this record
Where Mistral Large 2's numbers come from, and every name it appears under.
- Tracked since
- Apr 25, 2026
- Newest source mention
- Sep 10, 2026
Where the results come from
Verification: 39 scores · 14 independently verified · 22 aggregator-attributed · 3 vendor-reported. How these tiers are assigned
From 11 sources on 5 sites. Artificial Analysis supplies 22 of them; the 14 independently verified results come from 3 sites. Bars are coloured by trust tier.
- artificialanalysis.ai22
- storage.googleapis.com7
- huggingface.co6
- api.llm-stats.com3
- simple-bench.com1