Mistral AIProvisional

Mistral Medium 3.5

Mistral 3.5 / Medium · mistralai/Mistral-Medium-3.5-128B

Mistral frontier-class multimodal model optimized for agentic and coding use cases.

Objective score

22.2

Confidence

79%

Price evidence

Pricing evidence pending

Support this model Compare trend Official source

Scenario evidence

Six task-specific rankings

Feature development#58Obj. 22.20 · 0%Debug and repair#53Obj. 35.10 · 0%Refactoring#53Obj. 35.10 · 0%Code review#53Obj. 36.40 · 0%Large-repo agent work#59Obj. 18.90 · 0%Frontend / UI#53Obj. 35.10 · 0%

Evidence state

Signal coverage

Benchmarks: 2
Rank points: 8
Usage: 2
Agent: 0
Sources: 4

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: —
Artificial Analysis: 46.9
Openrouter Usage: 0
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#56 · 23

Aug 1#56 · 23

Aug 1#56 · 23

Jul 31#56 · 23

Jul 31#56 · 23

Jul 31#56 · 23

Usage signals

OpenRouter0%

Overall0%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

Official Mistral docs list Medium 3.5 as a frontier-class multimodal model for coding and agents.Artificial Analysis Coding Agents · ok WebDev Arena · ok Kilo leaderboard · ok Mistral model overview · ok