Inference
EN
Mistral

Mistral Large 2

Mistral Large 2 is a standard model from Mistral. 9 benchmarks count toward its index, in 5 categories.

  • Open weights
  • Standard
  • Input: text · file
  • Released 2024-07
RankedEnough results for an index.
IndexAll categories, out of 100.27.4±8.9Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.70/sMedian 67/s
First tokenSeconds to the first output token.1.8 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$2.00Median $0.60
Output / 1MUS dollars per 1M output tokens.$6.00Median $2.55
ContextMaximum tokens in one request.131KMedian 262K
EloLMArena rating and rank.1266±4 #288Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
mistralai/mistral-large-2407
Max outputMaximum output tokens per request.
105K
Knowledge cutoffLast date of training data.
31 Mar 2024
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.20
WeightsLink to the published weights.
Hugging Face (opens in a new tab) ↗
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
2 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
OpenRouterRouter$2.00$6.00131K
Snowflake CortexCloud$2.00$6.00128K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Run locally

122.61B parameters
16-bit
258.5 GB
8-bit
137.8 GB
4-bit
79.0 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy fits in 128 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted23.2—
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.1 counted36.8—
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.3 counted28.7243 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted18.2—
MathMath problems.3 counted22.0157 / 168

Results

9 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH level 5Math47.6% ±1.150 / 88
GPQA diamond · Epoch AIKnowledge50.2% ±2.7146 / 217
Critical Physics TasksReasoning0.0%150 / 214
τ²-Bench Tool-Agent-User EvaluationAgentic30.7%112 / 149
OTIS Mock AIME 2024-2025Math8.1% ±2.5157 / 200
Artificial Analysis Omniscience AccuracyKnowledge19.9%131 / 164
Artificial Analysis GPQA DiamondKnowledge48.6%178 / 199
Artificial Analysis IFBenchInstruction31.2%132 / 146
FrontierMath-2025-02-28-PrivateMath0.3% ±0.364 / 69
Artificial Analysis Humanity's Last ExamKnowledge3.3%216 / 222
FrontierMath-2025-02-28-PublicMath0.0% ±10.033 / 64

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseEpoch AICC BYmodels.devMIT

History

5 releases
Index28.2 → 27.4
23 Oct 202612 Nov 2026
Output / 1M$6.00 → $6.00
23 Oct 202612 Nov 2026

Questions

How much does Mistral Large 2 cost?
$2.00 per 1M input tokens, $6.00 per 1M output tokens.
How good is Mistral Large 2?
Its index is 27.4 out of 100. That is place 259 of 283 ranked models.
What is Mistral Large 2 best at?
Knowledge: 28.7 out of 100, place 243 of 268.
How fast is Mistral Large 2?
70 output tokens per second, 1.8 s to the first token.
What is the context window of Mistral Large 2?
131K tokens.
Is Mistral Large 2 open source?
Yes. Its weights are published.
When was Mistral Large 2 released?
July 2024.

Badge

Mistral Large 2 on Inference360: place 259 of 283, index 27.4
HTML
<a href="https://inference360.ai/models/mistral-large-2"><img src="https://inference360.ai/badges/mistral-large-2.svg" alt="Mistral Large 2 on Inference360: place 259 of 283, index 27.4" height="20"></a>
Markdown
[![Mistral Large 2 on Inference360: place 259 of 283, index 27.4](https://inference360.ai/badges/mistral-large-2.svg)](https://inference360.ai/models/mistral-large-2)

Compare with

Mistral Medium 327.1Gemini 2.5 Flash-Lite27.1Gemma 4 E4B28.2Mistral Small 3.124.2

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free

More from Mistral

All models
Mistral NemoUnrankedMistral 7B v0.3UnrankedMixtral 8x22B InstructUnrankedMixtral 8x22B Instruct v0.1UnrankedMistral LargeUnranked