Skip to content
llmwaves

Mistral Medium 3

Mistral AI · released May 7, 2025

ProprietaryTool useStructured outputVision

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

Specification

Context window
131K
Max output
105K
Knowledge cutoff
Mar 31, 2025
Parameters
Undisclosed
Licence
Proprietary
Serving providers
1
Moderated
No

Intelligence

9.0

37th percentile

Coding

—

Coding Index

Agentic

—

Agentic Index

Output speed

134 t/s

Median across providers

Latency

519ms

Time to first token

Cost per task

$0.07

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • MMLU-Pro
    76.0%
  • GPQA Diamond
    57.8%
  • LiveCodeBench
    40.0%
  • IFBench
    39.3%
  • AA-LCR (long context)
    31.3%
  • AIME 2025
    30.3%
  • τ²-bench (Telecom)
    24.3%
  • Humanity's Last Exam
    4.1%
  • Terminal-Bench Hard
    3.8%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
MMLU-Pro76.0%
GPQA Diamond57.8%
LiveCodeBench40.0%
IFBench39.3%
AA-LCR (long context)31.3%
AIME 202530.3%
τ²-bench (Telecom)24.3%
Humanity's Last Exam4.1%
Terminal-Bench Hard3.8%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Qwen3 Next 80B A3B Instruct9.6
Llama 4 Maverick9.3
Qwen3 Coder Next9.2
Mistral Medium 3.19.2
Mistral Medium 39.0
gpt-oss-20b9.0
LFM2.5-2.6B (free)8.4
GLM 4.6V8.4

Percentile among all indexed models

Intelligence37th
Mathematics32th
Terminal work24th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.4
Output / 1M tokens
$2
Cached input / 1M
$0.04
Blended 3:1
$0.8

One task, estimated

$0.07

Input tokens
50,000
Output tokens
25,000
Profile
Standard

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.