Mistral Medium 3.5 — benchmark results
Mistral's open 128B multimodal Medium 3.5 model unifying chat, reasoning, and coding. Provider: Mistral. Released 2025-12-02. Access: API.
Unified ELO 1635 ± 17, rank #403 of 1776 rated models, from 96 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 94.15 | Accuracy (%) | 92 |
| UGI Leaderboard | 49.47 | UGI Score | 89 |
| UGI - Natural Intelligence | 40.39 | NatInt Score | 87.5 |
| UGI - Writing | 45.47 | Writing Score | 86.3 |
| AA IFBench | 68.78 | Accuracy (%) | 82.6 |
| AA Terminal-Bench Hard | 33.33 | Accuracy (%) | 77.7 |
| Chatbot Arena (Text) | 1427 | Elo | 77.1 |
| AA Omniscience - Health | 27.3 | Accuracy (%) | 76.3 |
| Artificial Analysis Intelligence Index | 29.95 | Intelligence Index | 75.1 |
| AA Omniscience - Software Engineering (SWE) - Swift | 52 | Accuracy (%) | 74.8 |
| AA Long Context Reasoning | 61 | Accuracy (%) | 73.8 |
| AA Omniscience - Humanities & Social Sciences | 26.7 | Accuracy (%) | 72.1 |
Interactive version: theaggregate.ai/model?slug=mistral-medium-3-5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.