AI Tools Review

Mistral Large 4

By Mistral

Released: 2026-10-29

LLM
Mistral
Open Weights
Free
New

Mistral Large 4 is Mistral's open-weight AI model, released 29/10/2026. Mistral Large 4 is a natively multimodal mixture-of-experts model with about 1.05T total and 52B active parameters, released under the Mistral Ecosystem Open-Weight License (a modified MIT licence that needs a separate commercial licence for model-as-a-service use). The launch post is strongest on cybersecurity and agent-security results and prints few comparison numbers, with several charts (ChartQA Pro, SciCode-Verified, GDP.pdf, finance and legal evaluations) showing no readable scores, so those rows are left out. The docs page lists 5 November 2026 as its release date for the model (public preview began 6 October 2026). The model card and launch post disagree on Terminal-Bench 4 (41 against 28.3).

Visit Mistral Large 4

AI-Powered

Leverages advanced AI technology to deliver cutting-edge capabilities and results.

Fast & Efficient

Optimized performance ensures quick results without compromising on quality.

Purpose-Built

Specifically designed for llms tasks and workflows.

How does Mistral Large 4 score on independent benchmarks?

Mistral Large 4 ranks #24 of 28 models on the Artificial Analysis Intelligence Index (v5.0.1) with a score of 26.1, as measured on 22 November 2026.

Intelligence Index
26.1
AA v5.0.1
Coding Agent Index
40.6
in Mistral Vibe
Cost per task
$2.06
AA Intelligence Index task
Price per 1M tokens
$0.7 / $2.1
input / output

Where does Mistral Large 4 rank against other models?

How good is Mistral Large 4 at agentic coding?

How does Mistral Large 4 do on individual tests?

Evaluation (run by Artificial Analysis)Mistral Large 4Best of any model
Terminal-Bench 4.024.7%67.2%
FrontierCode 2.015%48.8%
Humanity's Last Examn/a74.3%
GDPval-AA (Elo)n/a1866

How has Mistral Large 4's score changed over time?

We have tracked Mistral Large 4 on Intelligence Index v5.0.1 since 22/11/2026. A point is added each day the score, coding index or price changes, so this chart fills in over time.

What does the Mistral Large 4 system card report?

Mistral Large 4 is a natively multimodal mixture-of-experts model with about 1.05T total and 52B active parameters, released under the Mistral Ecosystem Open-Weight License (a modified MIT licence that needs a separate commercial licence for model-as-a-service use). The launch post is strongest on cybersecurity and agent-security results and prints few comparison numbers, with several charts (ChartQA Pro, SciCode-Verified, GDP.pdf, finance and legal evaluations) showing no readable scores, so those rows are left out. The docs page lists 5 November 2026 as its release date for the model (public preview began 6 October 2026). The model card and launch post disagree on Terminal-Bench 4 (41 against 28.3).

These are Mistral AI's own published results (self-reported, with the vendor's harness and settings), so they are not directly comparable with other labs' numbers. Sources: Mistral Large 4 announcement (public preview) (06/10/2026), mistralai/Mistral-Large-4.0-1T05-A52B on Hugging Face, Mistral docs: mistral-large-4-0. Last checked 22/11/2026.

Coding

BenchmarkMistral Large 4Claude Opus 5GLM-5.3Kimi K3
DeepSWE v1.1Launch post chart61.7%n/an/an/a
SWE-Atlas-QnALaunch post chart59.4%n/an/an/a
Terminal-Bench 4Launch post chart (the Hugging Face card lists 41 on the same benchmark name)28.3%n/an/an/a
Terminal-Bench 4 (Hugging Face card)Value listed on the model card metadata, which differs from the launch post chart41%n/an/an/a
Coding Agent Index (Artificial Analysis)Launch post: ahead of DeepSeek V4 Pro 0813 and Qwen3.8 Max (scores not printed)49.8%n/an/an/a
Coding Agent Index (Hugging Face card)Card also states 47% fewer tokens per task on average48%n/an/an/a
CWE-Bench resolve rateValue listed on the model card46.3%n/an/an/a
Terminal-Bench Science v0.1Value listed on the model card4.3%n/an/an/a
Surge AI blind human coding evaluationPreview model; second of five models tested3.74 points (1 to 5)4.223.63.59

Agents & tool use

BenchmarkMistral Large 4Claude Opus 5GLM-5.3Kimi K3
AutomationBench (657 business workflows)Launch post: ahead of Kimi K3, MiMo-V2.6-Pro and DeepSeek V4 Pro (scores not printed)59.9%n/an/an/a
AA-BriefcaseLaunch post: ahead of DeepSeek V4 Pro (score not printed)1393 Elon/an/an/a
CybenchShare of 40 challenges solved93%n/an/an/a
Artificial Analysis Cyber Index: reproduce-and-patch real vulnerabilitiesHighest of any model on the test per the launch post82%n/an/an/a

Multimodal

BenchmarkMistral Large 4Claude Opus 5GLM-5.3Kimi K3
Dense 200 (visual grounding)42%n/an/an/a

Safety & honesty

BenchmarkMistral Large 4Claude Opus 5GLM-5.3Kimi K3
B3 AI Security Benchmark (Lakera)Lakera public weak-agent dataset93.3 % of attacks resistedn/an/an/a
KORABenchHighest among open-source models measured, per the launch post1.691 points (maximum 2, Exemplary)n/an/an/a

Other

BenchmarkMistral Large 4Claude Opus 5GLM-5.3Kimi K3
Artificial Analysis Intelligence Index v5Value listed on the model card26 pointsn/an/an/a

What did safety testing find for Mistral Large 4?

Safety level: No framework rating published; Mistral reports security and alignment benchmarks only

  • Resists 93.3% of attacks on Lakera's B3 AI Security Benchmark.
  • Scores 1.691 out of 2 on KORABench, the highest among open-source models measured.
  • Cyber refusal rate on JailbreakBench, StrongREJECT and AgentHarm is described as higher than all open-source models, with no figure given.

Independent figures: Artificial Analysis, refreshed daily on our AI model benchmarks page. Full analysis: our Mistral Large 4 deep dive.

Mistral Model Timeline

Mistral Large 4Current

1M tokens context

Mistral Medium 3.5

262k tokens context

Specifications

pricing$0.7/$2.1 per 1M tokens (input/output)
context Window1M tokens