Best Coding Model
Mistral AIProvisional

Ministral 3 3B

Mistral / Ministral 3 3B · ministral-3-3b-25-12

Automatically tracked from Mistral AI's official model catalog.

Objective score

3.7

Confidence

76%

Price evidence

$0.1 input / $0.1 output per 1M tokens

Other primary tiers in this family

Evidence state

Signal coverage

Benchmarks
1
Rank points
7
Usage
0
Agent
0
Sources
4

Objective evidence

Benchmarks and public signals

Swebench
Livecodebench
Aider
Artificial Analysis
4.8
Openrouter Usage
Kilo Usage

Persistent history

Recent ranking points

Sep 15#82 · 5
Sep 15#82 · 5
Sep 15#82 · 5
Sep 14#82 · 5
Sep 14#82 · 5
Sep 14#82 · 5

Usage signals

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

Agent and tool signals

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