Mistral Large 3
MistralMistralOpen WeightApache 2.0 · Commercial OK
Description
Mistral Large 3 is a state-of-the-art general-purpose Multimodal granular Mixture-of-Experts model with 41B active parameters and 675B total parameters trained from scratch with 3000 H200s. This model is the instruct post-trained version, fine-tuned for instruction tasks, making it ideal for chat, agentic and instruction based use cases. Designed for reliability and long-context comprehension - It is engineered for production-grade assistants, retrieval-augmented systems, scientific workloads, and complex enterprise workflows.
Release Date
2025-12-02
Parameters
675.0B
Context Length
262K
Modalities
image, text
Capability Radar
30
general
31
coding
43
reasoning
44
science
39
agents
85
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 410 | 33.0 | AA |
| General Ranking | 404 | 34.0 | AA |
| Science | 379 | 40.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Chat
MM-MT-Bench
84.90 / 100SR
Factuality
SimpleQA
23.8%SR
General
TriviaQA
74.9%SR
Wild Bench
68.5%SR
Arena Hard
55.1%SR
Language
MMMLU
85.5%SR
MMLU-Redux
82.0%SR
Math
MATH
90.4%SR
MATH (CoT)
67.6%SR
AMC_2022_23
52.0%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
43.9%SR
LiveCodeBench
34.4%SR
AA Evaluation Indices
(Artificial Analysis)Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))80.7
Gpqa(NYU + Cohere + Anthropic (2023))68.0
Livecodebench(UC Berkeley + MIT + Cornell (2024))46.5
Math Index(Artificial Analysis)38.0
Aime 25(MAA (Mathematical Association of America))38.0
Scicode(UIUC + Argonne National Lab (2024))36.6
Ifbench(Google Research (2023))36.2
Lcr(Artificial Analysis)36.0
Tau2(Sierra + U Toronto + Vector Institute (2025))24.6
Coding Index(Artificial Analysis)20.1
Terminalbench Hard(Stanford × Laude Institute (2026))15.9
Terminalbench V2 112.0
Intelligence Index(Artificial Analysis)9.3
Tau Banking5.8
Hle(Center for AI Safety + Scale AI (2025))4.2
Terminalbench V4 00.0
LLM Stats Category Scores
(LLM Stats (zeroeval))Multimodal85
Communication43
Chat43
General11
Language80
Math80
Reasoning70
Creativity60
Writing60
Pricing
Input Price$0.5 / 1M tokens
Output Price$1.5 / 1M tokens
Blended Price (3:1)$0.75 / 1M tokens
Cache Read Price$0.05 / 1M tokens
Speed
Tokens/sec75.9
Time to First Token0.72s
Time to Answer0.72s
Provider Price Ranking
Provider Price Ranking
8 providers
Cheapest: MistralMost Expensive: 302.AI
ProviderInputOutput
1MistralPRIMARY
$0.5
$1.5
2OpenRouter
$0.5
$1.5
3Kilo Gateway
$0.5
$1.5
4DevPass (LLM Gateway)
$0.5
$1.5
5Pioneer
$0.5
$1.5
6Opper
$0.5
$1.5
7Cortecs
$0.613
$1.838
8302.AI
$1.1
$3.3
Compare pricing across different API providers for this model.