Skip to main content

Mistral Large 3

MistralEstablishedReleased Dec 2, 2025
Overall Score
Est. 49Prov. #68 of 119
Arena Elo
1415
Categories Ranked
8of 8
Price (1M tokens)
$0.5 in / $1.5 out
Speed
48tok/s
Context
128K
ProprietarySelf-hostNon-Reasoning
Confidence
base

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Mistral Large 3
API / mo$1,500
Self-host / mo$9,110
Break-even380M/day
Model the full break-even

According to BenchLM.ai, Mistral Large 3 ranks #68 out of 119 models on the provisional leaderboard with an overall score of 49/100. It does not yet have enough sourced coverage for BenchLM's verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Mistral Large 3 is a proprietary model with a 128K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 17 of 225 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Multimodal & Grounded (#32), while its weakest is Knowledge (#70). This performance profile makes it particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Ranking Distribution

Category rank across 8 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#64
38.2/ 100
Weight: 22%4 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#65
38.4/ 100
Weight: 20%3 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#51
52.1/ 100
Weight: 17%2 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#70
41.5/ 100
Weight: 12%6 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#40
64.4/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#55
59.6/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#32
67.0/ 100
Weight: 12%1 benchmark
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#52
67.2/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1415CI: ±3.642,553 votes
Coding1468CI: ±6.59,554 votes
Math1402CI: ±11.42,737 votes
Instruction Following1405CI: ±6.011,837 votes
Creative Writing1377CI: ±7.96,517 votes
Multi-turn1421CI: ±7.47,332 votes
Hard Prompts1432CI: ±4.723,584 votes
Hard Prompts (English)1440CI: ±6.111,512 votes
Longer Query1417CI: ±6.111,900 votes

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Frequently Asked Questions

How does Mistral Large 3 perform overall in AI benchmarks?

Mistral Large 3 currently ranks #68 out of 119 models on BenchLM's provisional leaderboard with an overall score of 49 (estimated). It is created by Mistral and features a 128K context window.

Is Mistral Large 3 good for knowledge and understanding?

Mistral Large 3 ranks #70 out of 119 models in knowledge and understanding benchmarks with an average score of 41.5. There are stronger options in this category.

Is Mistral Large 3 good for coding and programming?

Mistral Large 3 ranks #65 out of 119 models in coding and programming benchmarks with an average score of 38.4. There are stronger options in this category.

Is Mistral Large 3 good for reasoning and logic?

Mistral Large 3 ranks #51 out of 119 models in reasoning and logic benchmarks with an average score of 52.1. There are stronger options in this category.

Is Mistral Large 3 good for agentic tool use and computer tasks?

Mistral Large 3 ranks #64 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 38.2. There are stronger options in this category.

Is Mistral Large 3 good for multimodal and grounded tasks?

Mistral Large 3 ranks #32 out of 119 models in multimodal and grounded tasks benchmarks with an average score of 67. There are stronger options in this category.

Is Mistral Large 3 good for instruction following?

Mistral Large 3 ranks #52 out of 119 models in instruction following benchmarks with an average score of 67.2. There are stronger options in this category.

Does Mistral Large 3 have full benchmark coverage on BenchLM?

Not yet. Mistral Large 3 currently has 17 published benchmark scores out of the 225 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Mistral Large 3?

Mistral Large 3 has a context window of 128K, which determines how much text it can process in a single interaction.

Last updated: June 2, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.