Inference
EN
Mistral

Mistral Medium 3.5

Mistral Medium 3.5 is a model from Mistral. 9 benchmarks count toward its index, in 4 categories.

  • Open weights
  • Input: text · image · file
  • Released 2026-04
RankedEnough results for an index.
IndexAll categories, out of 100.42.7±8.9Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.92/sMedian 67/s
First tokenSeconds to the first output token.0.6 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$1.50batch $0.75Median $0.60
Output / 1MUS dollars per 1M output tokens.$7.50batch $3.75 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.262KMedian 262K
EloLMArena rating and rank.1421±6 #114Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
mistralai/mistral-medium-3-5
Max outputMaximum output tokens per request.
210K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
—
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.
1 provider
ProviderTypeMaker, cloud, host or router.InputOutputContext
OpenRouterRouter$1.50$7.50262K

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

Run locally

127.7B parameters
16-bit
269.2 GB
8-bit
143.5 GB
4-bit
82.3 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.3 counted47.1153 / 218
CodingCode writing and repair.3 counted47.1154 / 209
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.2 counted24.3259 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.1 counted50.3—

Results

9 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Terminal-Bench 2.0 · Vals AIAgentic30.3% ±4.944 / 66
MMLU ProKnowledge75.3% ±0.4109 / 135
SWE-benchCoding66.4% ±2.171 / 87
Agent Arena task outcomeAgentic−16.849 / 54
Terminal-Bench 2.1 · Vals AIAgentic39.0% ±2.769 / 75
Code MigrationCoding5.1% ±1.471 / 77
ProofBench v1.1Math9.0% ±2.950 / 54
Agent Arena steerabilityAgentic−16.950 / 54
Agent Arena command recoveryAgentic−20.447 / 50
Vibe Code Bench v1.1Coding2.9% ±1.7116 / 123
GPQA Diamond · Vals AIKnowledge34.8% ±2.4131 / 135
CorpFin v2Finance58.8% ±1.082 / 131
Finance Agent v1.1Finance46.1% ±2.933 / 51
TaxEval v2Finance68.0% ±0.9103 / 143
MedCodeHealthcare33.8% ±1.183 / 106
Finance Agent (v2)Finance32.1% ±1.069 / 79
MedScribeHealthcare67.7% ±2.099 / 109
Legal Research BenchLegal9.1% ±2.082 / 90
Tax Agent BenchFinance4.5% ±1.579 / 82
SAGEEducation72.0% ±2.228 / 29
MortgageTaxFinance28.9% ±0.894 / 97
EMBFinance11.2% ±1.673 / 75
CaseLaw v2Legal44.2% ±1.152 / 53

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedLMArenaCC BY 4.0models.devMIT

History

5 releases
Index43.4 → 42.7
23 Oct 202612 Nov 2026
Output / 1M$7.50 → $7.50
23 Oct 202612 Nov 2026

Questions

How much does Mistral Medium 3.5 cost?
$1.50 per 1M input tokens, $7.50 per 1M output tokens.
How good is Mistral Medium 3.5?
Its index is 42.7 out of 100. That is place 195 of 283 ranked models.
What is Mistral Medium 3.5 best at?
Agentic: 47.1 out of 100, place 153 of 218.
How fast is Mistral Medium 3.5?
92 output tokens per second, 0.6 s to the first token.
What is the context window of Mistral Medium 3.5?
262K tokens.
Is Mistral Medium 3.5 open source?
Yes. Its weights are published.
When was Mistral Medium 3.5 released?
April 2026.

Badge

Mistral Medium 3.5 on Inference360: place 195 of 283, index 42.7
HTML
<a href="https://inference360.ai/models/mistral-mistral-medium-3-5"><img src="https://inference360.ai/badges/mistral-mistral-medium-3-5.svg" alt="Mistral Medium 3.5 on Inference360: place 195 of 283, index 42.7" height="20"></a>
Markdown
[![Mistral Medium 3.5 on Inference360: place 195 of 283, index 42.7](https://inference360.ai/badges/mistral-mistral-medium-3-5.svg)](https://inference360.ai/models/mistral-mistral-medium-3-5)

Compare with

Claude Sonnet 443.0Mistral Large 460.7

Lower price

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

More from Mistral

All models
Mistral Medium 3.5 128B50.3Mistral Small 437.9LeanstralUnrankedMistral Small 4 (Reasoning)UnrankedLeanstral 1.5Unranked