Mistral Large 4

Released
2026-10-06
Last refreshed
2026-11-20
Status
Researched today
Open weightsCommercial use: restrictedMultimodalCodingRAGAgentsLong contextVisionJSON / Tool useVisionAgentCoding
MistralAI releases · 25 in the last 12 months · this family litChangelog →
Specifications
Released
2026-10-06
Context
1M
Parameters
1.05T (49B active)
Architecture
Mixture of Experts
Specialization
general
Openness
Open weights
Weights
Available
Code
Unknown
Training
Multi-stage
Created by

Enterprise AI solutions for trust and transparency.

Paris, France
Founded 2023
Website
Pricing
Output / 1M
$2.10
Input / 1M
$0.700

Cheapest of 3 routes · Mistral AI Studio · cache read $0.070

About

Mistral Large 4 (API id mistral-large-4-0, public preview launched 6 October 2026) is Mistral AI's multimodal mixture-of-experts model: 1.05T total parameters, 49B active per token (52B including embeddings and output layers), and a 1.6B vision encoder, with a 1M-token context window. On 29 October 2026 Mistral released the weights of an improved version on Hugging Face under the Mistral Ecosystem Open-Weight License (a modified MIT license that requires a separate commercial license to run a Model-as-a-Service business).

Providers(3)

Compare all 3

Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
Mistral AI Studio$0.700$2.10read $0.070
Serverless
OpenRouter$0.700$2.10read $0.070
Serverless
Vercel AI Gateway$0.700$2.10read $0.070
Serverless

Available via routers & gateways(10)

Capabilities

VisionMultimodalJSON / Tool useStructured OutputsPrompt CachingBatch API

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(7)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
88.1diamondObserved 2026-10-17
Configuration: mistral-large-4 (High)
Harness: Epoch AI Inspect harness (GPQA Diamond, 198 Q)
Evaluator: Epoch AI
Confidence: confirmed
Notes: Epoch AI-run evaluation (evaluator of record), from Epoch AI Benchmarking Hub data download https://epoch.ai/data/benchmark_data.zip (file gpqa_diamond.csv, row 'mistral-large-4-0_high', run started 2026-10-12). Epoch data is CC BY 4.0: credit 'Epoch AI, Capabilities Benchmarking Hub'. Retrieved 2026-10-17.
26.8FrontierMath Tier 4 v2 (private)Observed 2026-10-17
Configuration: mistral-large-4 (High)
Harness: Epoch AI FrontierMath Tier 4 v2 private set
Evaluator: Epoch AI
Confidence: confirmed
Notes: Epoch AI-run evaluation (evaluator of record), from Epoch AI Benchmarking Hub data download https://epoch.ai/data/benchmark_data.zip (file frontiermath_tier_4_v2.csv, row 'mistral-large-4-0_high', run started 2026-10-12). Epoch data is CC BY 4.0: credit 'Epoch AI, Capabilities Benchmarking Hub'. Retrieved 2026-10-17.
54.7Finance Agent v2 (Vals benchmark_id finance_agent_v2, version 2)Observed 2026-10-17
Configuration: Vals AI default provider Mistral AI; temperature 1, top-p 0.95, max output 256,000, reasoning effort high
Harness: Vals AI Finance Agent harness (Valkyrie)
Evaluator: Vals AI
Confidence: third-party
Cost/task: $1.20
Notes: Vals AI leaderboard (https://www.vals.ai/benchmarks/fabv2), page 'Updated 10/16/2026', retrieved 2026-10-17. Vals model page https://www.vals.ai/models/mistralai_mistral-large-4 shows the hyperparameters. Accuracy. The lab's restatement (https://mistral.ai/news/mistral-large-4/) reads 54.7 (chart read); it matches after rounding and is not the source of this row.
15.8Harvey's Legal Agent Benchmark v1 (Vals benchmark_id legal_agent_benchmark)Observed 2026-10-17
Configuration: Vals AI default provider Mistral AI; temperature 1, top-p 0.95, max output 256,000, reasoning effort high
Harness: Harvey generation and grading protocol, run by Vals on Valkyrie, internet disabled
Evaluator: Vals AI
Confidence: third-party
Cost/task: $4.18
Notes: Vals AI leaderboard (https://www.vals.ai/benchmarks/hlab), page 'Updated 10/16/2026', retrieved 2026-10-17. Vals model page https://www.vals.ai/models/mistralai_mistral-large-4 shows the hyperparameters. Metric is the task all-pass rate: a task passes only if 100% of its criteria pass, averaged over two LLM judges (GPT 5.5 medium reasoning, Claude Sonnet 4.6). Vals model page: ±2.96. The lab's restatement (https://mistral.ai/news/mistral-large-4/) reads 15.8 (chart read, "Vals.ai Harvey LAB"); it matches after rounding and is not the source of this row.
1434.0text_style_control overall 2026-10-22 (style control, default view)Observed 2026-10-26
Configuration: Mistral Large 4
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena text style control leaderboard, overall category, published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'Mistral Large 4': rank 111, Arena Score 1433.8 (95% CI 1427.4-1440.3), 10331 votes. Retrieved 2026-10-26.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

1252.0vision_style_control overall 2026-10-19 (style control, default view)Observed 2026-10-26
Configuration: Mistral Large 4
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena vision style control leaderboard, overall category, published 2026-10-19 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'Mistral Large 4': rank 52, Arena Score 1251.9 (95% CI 1232.6-1271.3), 1008 votes. Retrieved 2026-10-26.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

1364.0text creative_writing 2026-10-22Observed 2026-10-22
Configuration: Mistral Large 4
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Mistral Large 4' (category creative_writing in text/latest-00000-of-00001.parquet): rank 152 of 416, rating 1363.8 (95% CI 1350.9-1376.6), 2383 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

Migration checks

No linked migration route is available for this model yet.

API versions

mistral-large-4-0mistral-large-4ML4mistralai/mistral-large-4-0mistral/mistral-large-4