Inference
EN
Mistral

Mistral Medium 3

Mistral Medium 3 is a standard model from Mistral. 12 benchmarks count toward its index, in 7 categories.

  • Closed weights
  • Standard
  • Input: text · image · file
  • Released 2025-05
RankedEnough results for an index.
IndexAll categories, out of 100.27.1±5.2Median 51.0
CoverageIndex weight that has results.95%
SpeedOutput tokens per second.94/sMedian 67/s
First tokenSeconds to the first output token.0.6 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.40Median $0.60
Output / 1MUS dollars per 1M output tokens.$2.00Median $2.55
ContextMaximum tokens in one request.131KMedian 262K
EloLMArena rating and rank.1370±5 #189Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
mistralai/mistral-medium-3
Max outputMaximum output tokens per request.
105K
Knowledge cutoffLast date of training data.
31 Mar 2025
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.04
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
1 provider
ProviderTypeMaker, cloud, host or router.InputOutputContext
OpenRouterRouter$0.40$2.00131K

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

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted18.9—
CodingCode writing and repair.1 counted9.3—
ReasoningLogic problems and puzzles.2 counted32.8198 / 227
MultimodalTasks with images and text.1 counted24.1—
KnowledgeFacts and expert knowledge.3 counted31.1235 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted25.7—
MathMath problems.3 counted32.2140 / 168

Results

12 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH level 5Math81.6% ±0.927 / 88
GPQA diamond · Epoch AIKnowledge59.5% ±2.8129 / 217
OTIS Mock AIME 2024-2025Math32.2% ±6.0131 / 200
Critical Physics TasksReasoning0.0%150 / 214
Artificial Analysis IFBenchInstruction39.3%107 / 146
Artificial Analysis GPQA DiamondKnowledge57.8%161 / 199
Artificial Analysis Long Context ReasoningReasoning31.3%179 / 217
τ²-Bench Tool-Agent-User EvaluationAgentic24.3%124 / 149
Artificial Analysis Omniscience AccuracyKnowledge18.3%139 / 164
Artificial Analysis MMMU-ProMultimodal53.0%100 / 113
Artificial Analysis Humanity's Last ExamKnowledge4.1%199 / 222
FrontierMath-2025-02-28-PrivateMath0.3% ±0.364 / 69
LiveCodeBench v6Coding30.3%58 / 59
FrontierMath-2025-02-28-PublicMath0.0%33 / 64

Sources

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

History

5 releases
Index27.9 → 27.1
23 Oct 202612 Nov 2026
Output / 1M$2.00 → $2.00
23 Oct 202612 Nov 2026

Questions

How much does Mistral Medium 3 cost?
$0.40 per 1M input tokens, $2.00 per 1M output tokens.
How good is Mistral Medium 3?
Its index is 27.1 out of 100. That is place 260 of 283 ranked models.
What is Mistral Medium 3 best at?
Math: 32.2 out of 100, place 140 of 168.
How fast is Mistral Medium 3?
94 output tokens per second, 0.6 s to the first token.
What is the context window of Mistral Medium 3?
131K tokens.
Is Mistral Medium 3 open source?
No. Its weights are not published.
When was Mistral Medium 3 released?
May 2025.

Badge

Mistral Medium 3 on Inference360: place 260 of 283, index 27.1
HTML
<a href="https://inference360.ai/models/mistral-medium-3"><img src="https://inference360.ai/badges/mistral-medium-3.svg" alt="Mistral Medium 3 on Inference360: place 260 of 283, index 27.1" height="20"></a>
Markdown
[![Mistral Medium 3 on Inference360: place 260 of 283, index 27.1](https://inference360.ai/badges/mistral-medium-3.svg)](https://inference360.ai/models/mistral-medium-3)

Compare with

Gemini 2.5 Flash-Lite27.1Phi-4-reasoning27.1Mistral Large 227.4Devstral Small28.2Mistral 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
Devstral Small28.2Magistral Medium33.7Magistral Small31.4Mistral Small 3.2 24BUnrankedMistral Small 3.1 24BUnranked