Skip to content

Mistral Medium 3

MistralProprietaryNon-reasoningProvisionalReleased May 7, 2025Input: text, image, file
Compare with Granite-4.0-H-1BSource scores ↗OpenRouter ↗
Overall score
28.8
Rank 187 of 222 · 14.4–43.1
Context window
128K
128,000 tokens
Price per 1M tokens
$0.40 in · $2.00 out
Source: BenchLM
Blended price
$0.80
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Reasoning46.5
  2. 2Instruction following#10545.5
  3. 3Multimodal42.6
  4. 4Knowledge40.4
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (2)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Coding

LiveCodeBench v630.3#46 of 46

Multimodal

Design Arena Website1080#81 of 91

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price (BenchLM)$0.40$2.00—
OpenRouter mistralai/mistral-medium-3$0.40$2.00$0.040

Mistral's official Mistral Medium 3 model card lists $0.40 input / $2.00 output per million tokens in Mistral AI Studio.

Arena ratings

Human-preference ratings from LMArena. Best-rated variant shown.

Vision(2505)1157#117 · 10.8K votes

Speed

Measured by us through OpenRouter (median of trials).

Not measured yet.

Related models

Similar score