# Mistral Medium 3 Benchmark Scores & Performance

> Mistral Medium 3 by Mistral scores 32.53/100 overall, ranking #210 out of 411 AI models.

Canonical page: https://benchlm.ai/models/mistral-medium-3

Last updated: September 4, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Mistral |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | 128K |
| Overall Score | 32.53/100 |
| Overall Rank | #210 of 411 |

## Family & Coverage

- Family: Mistral Medium 3
- Variant: base
- Benchmarks covered: 13 of 422
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [τ²-bench results](/benchmarks/tau2-bench) | 24.3% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-SciCode](/benchmarks/aascicode) | 33.1% |

## Multimodal & Grounded Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-MMMU-Pro](/benchmarks/aammmupro) | 53.0% |
| [Design Arena Website](/benchmarks/designarenawebsite) | 1094 |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 31.7% |
| [CritPt](/benchmarks/critpt) | 0.0% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 12.5% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 57.8% |
| [AA-HLE](/benchmarks/aahle) | 4.1% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -31.4% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 18.3% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 60.9% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-IFBench](/benchmarks/aaifbench) | 39.3% |

## Other Mistral Models

- [Mistral Medium 3.5 128B](/models/mistral-medium-3-5-128b) - Score: 48.95
- [Ministral 3 14B (Reasoning)](/models/ministral-3-14b-reasoning) - Score: 48.92
- [Mistral Large 3](/models/mistral-large-3) - Score: 48.77
- [Mistral Small 4](/models/mistral-small-4) - Score: 46.82
- [Mistral 8x7B](/models/mistral-8x7b) - Score: 44.66
- [Ministral 3 8B (Reasoning)](/models/ministral-3-8b-reasoning) - Score: 40.17
- [Ministral 3 3B (Reasoning)](/models/ministral-3-3b-reasoning) - Score: 39.32
- [Mistral 8x7B v0.2](/models/mistral-8x7b-v0-2) - Score: 38.95
- [Mistral Large 2](/models/mistral-large-2) - Score: 37.56
- [Ministral 3 14B](/models/ministral-3-14b) - Score: 33.77
- [Mixtral 8x22B Instruct v0.1](/models/mixtral-8x22b-instruct-v0-1) - Score: 26.61
- [Ministral 3 8B](/models/ministral-3-8b) - Score: 20.61
- [Ministral 3 3B](/models/ministral-3-3b) - Score: 18.27
- [Mistral 7B v0.3](/models/mistral-7b-v0-3) - Score: 8.65
- [Leanstral](/models/leanstral) - Score: not computed
- [Mistral Small 4 (Reasoning)](/models/mistral-small-4-reasoning) - Score: not computed