← Back to all models
M

Ministral 3 3B

by Mistral AI
Efficient Free & Open Source 🏆 Ranked #83 of 85
48.5
Overall Score
out of 100
About

Mistral AI's ultra-compact 3B model optimised for speed and cost-effectiveness. Ideal for edge deployment and high-volume applications where minimal latency matters most.

Key Metrics
Context Window
128K
tokens
Avg Response
160
milliseconds
Input Cost
$0.02
per million tokens
Output Cost
$0.02
per million tokens
Arena ELO
1115
Chatbot Arena rating
MT-Bench
7.5
out of 10
Benchmark Scores
MMLU
61.0%
HumanEval
55.0%
MATH
42.0%
GPQA
23.0%
MT-Bench
75.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Very fast ✓ Tiny footprint ✓ Open source ✓ Edge deployment ✓ Low cost
Limitations
⚠ Limited capability ⚠ Not for complex tasks ⚠ Small knowledge base
Ideal Use Cases
Edge AI Mobile Fast chatbots Classification Simple summarisation
Model Details
Provider Mistral AI
Released 2025-04-01
Type Free & Open Source
Multimodal No
Tier Efficient
Global rank #83 / 85
Pricing (USD)
Input tokens $0.02/M
Output tokens $0.02/M
Per 1,000 tokens ≈ $0.0000 input / $0.0000 output
All Benchmarks
MMLU 61.0%
HumanEval 55.0%
MATH 42.0%
GPQA 23.0%
MT-Bench 7.5/10
Arena ELO 1115
Compare this model View Rankings

You might also consider