LLM Reference

Mistral Large 2

Released
2025-11-25
Last refreshed
2026-06-16
Status
Researched 86d ago
Open weightsCommercial use: non-commercialMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Mistral Large 2 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 128k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Released
2025-11-25
Context
128k
Parameters
123B
Architecture
Decoder Only
Knowledge cutoff
2025-07
Specialization
general
Openness
Open weights
License
Mistral LicenseCommercial use: non-commercial
Weights
Unknown
Code
Unknown
Training
Fine-tuned
Created by

Enterprise AI solutions for trust and transparency.

Paris, France
Founded 2023
Website
Pricing
Output / 1M
$2.40
Input / 1M
$0.480

Cheapest of 3 routes · AWS Bedrock

About

Advanced reasoning and coding model, multilingual with native function calling and JSON output

Mistral Large 2 is an open-weight model in the Mistral Large family. The structured metadata tracks a 128k-token context window, multimodal input, function calling, tool use, and structured outputs. This page tracks provider routes through IBM watsonx, AWS Bedrock, and Mistral AI Studio, with the cheapest tracked route listed at $0.48 input and $2.4 output per 1M tokens. Headline tracked benchmarks include HellaSwag 93.8, HumanEval 84.8, and Massive Multitask Language Understanding 84.0.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 3

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

ProviderInput / 1MOutput / 1MBatch in / outRoute
AWS Bedrock$0.480$2.40-
Serverless
IBM watsonx$2.00$6.00-
Serverless
Mistral AI Studio--$1.00 / $3.00
ServerlessPartial

Available via routers & gateways(11)

Capabilities

VisionMultimodalFunction CallingTool UseStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(6)

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
HellaSwag93.810-shotObserved 2026-03-06Source
HumanEval84.8pass@1Observed 2026-03-06Source
Massive Multitask Language Understanding84.05-shotObserved 2026-03-06Source
Chatbot Arena1265.0Observed 2026-04-15Source
BFCL38.4Observed 2026-04-14Source
MMLU PRO69.7Observed 2026-04-14Source

Migration checks

No linked migration route is available for this model yet.

Compare Mistral Large 2 with other models

Show all 57 popular comparisonssorted by 7-day search impressions
Mistral Large 2 vs o360Mistral Large 2 vs GPT-5.5 Instant59Mistral Large 2 vs GPT-4o (05-13)58Mistral Large 2 vs GLM-5.146Mistral Large 2 vs GPT-4 Vision Preview43Mistral Large 2 vs MiniCPM-V 4.641Mistral Large 2 vs Gemini 2.5 Pro40Mistral Large 2 vs Llama 3 8B Instruct40Mistral Large 2 vs DeepSeek R139Mistral Large 2 vs Llama 3.2 1B Instruct38Mistral Large 2 vs Gemini 2.5 Flash36Mistral Large 2 vs Together AI - Llama 3 8B Lite35Mistral Large 2 vs Trinity-Large-Thinking33Mistral Large 2 vs Codex 133Mistral Large 2 vs Qwen3.6-35B-A3B32Mistral Large 2 vs Claude 3.7 Sonnet31Mistral Large 2 vs Qwen2.5-72B-Instruct30Mistral Large 2 vs Gemma 7B Instruct29Mistral Large 2 vs DeepSeek V3.126Mistral Large 2 vs Grok 3 Mini26Mistral Large 2 vs GPT-5.425Mistral Large 2 vs GLM-525Mistral Large 2 vs Qwen3-Max23Mistral Large 2 vs Kimi K2.522Mistral Large 2 vs Claude Opus 4.622Mistral Large 2 vs Llama 3.3 70B22Mistral Large 2 vs Qwen3.5-397B-A17B21Mistral Large 2 vs Llama 2 13B Chat21Mistral Large 2 vs Command R+19Mistral Large 2 vs GPT-414Mistral Large 2 vs Hunyuan Hy3 Preview14Mistral Large 2 vs o3 Mini13Mistral Large 2 vs Qwen2.5-72B12Mistral Large 2 vs GLM-5 Turbo12Mistral Large 2 vs Qwen3.5-35B-A3B9Mistral Large 2 vs Qwen3.5-122B-A10B9Mistral Large 2 vs GPT-5.4 Pro9Mistral Large 2 vs GPT-4 Turbo9Mistral Large 2 vs Claude Opus 4.58Mistral Large 2 vs Mistral Nemotron8Mistral Large 2 vs GPT-5.28Mistral Large 2 vs o3 Deep Research8Mistral Large 2 vs Grok 4.208Mistral Large 2 vs DeepSeek R1 05288Mistral Large 2 vs Grok 4.38Mistral Large 2 vs Llama 4 Maverick 17B Instruct FP88Mistral Large 2 vs GPT-4o (08-06)6Mistral Large 2 vs Phi-4 Mini Flash Reasoning4Mistral Large 2 vs Qwen3.5-27B4Mistral Large 2 vs GPT-14Mistral Large 2 vs Qwen3-235B-A22B3Mistral Large 2 vs Llama Guard 2 8B3Mistral Large 2 vs ELYZA Japanese Llama 2 7B3Mistral Large 2 vs Xiaomi MiMo-V2.5-Pro2Mistral Large 2 vs Llama Guard 3 1B1Mistral Large 2 vs DeepSeek R1 Lite1Mistral Large 2 vs Qwen3-30B-A3B1

Frequently asked questions

What is the context window of Mistral Large 2?

Mistral Large 2 has a context window of 128k tokens.

How much does Mistral Large 2 cost?

Mistral Large 2 pricing ranges from $0.48/1M to $2/1M input tokens depending on the provider.

When was Mistral Large 2 released?

Mistral Large 2 was released on 2025-11-25.

Which providers offer Mistral Large 2?

Mistral Large 2 is available from 3 providers: IBM watsonx, AWS Bedrock, Mistral AI Studio.

What benchmarks has Mistral Large 2 been tested on?

Mistral Large 2 has been evaluated on 6 benchmarks, including HellaSwag, HumanEval, Massive Multitask Language Understanding, Chatbot Arena, BFCL.