Mistral Medium 3
Mistral AI · released May 7, 2025
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-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%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| 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% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- 9.6
- Llama 4 MaverickMeta9.3
- Qwen3 Coder NextQwen9.2
- Mistral Medium 3.1Mistral AI9.2
- Mistral Medium 3Mistral AI9.0
- gpt-oss-20bOpenAI9.0
- LFM2.5-2.6B (free)Liquid8.4
- GLM 4.6VZ.ai8.4
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Qwen3 Next 80B A3B Instruct | 9.6 |
| Llama 4 Maverick | 9.3 |
| Qwen3 Coder Next | 9.2 |
| Mistral Medium 3.1 | 9.2 |
| Mistral Medium 3 | 9.0 |
| gpt-oss-20b | 9.0 |
| LFM2.5-2.6B (free) | 8.4 |
| GLM 4.6V | 8.4 |
Percentile among all indexed models
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.