- Intelligence
- 6.0
- Rank 660 of 782 measured models
- Coding
- 14.4
- Rank 251 of 301 measured models
- Price/1M
- $0.20
- Rank 188 of 740 measured models
- Context window
- 262K
- Rank 449 of 1325 measured models
Ministral 3 14B 2512 scores 6.0 on the Artificial Analysis Intelligence Index, ranking 660th of 782 measured models. The closest models on this index are DeepSeek-Coder-V2 (6.0), Granite 4.0 H Small (6.0), and Hermes 3 - Llama-3.1 70B (6.0). At $0.20 per million tokens (3:1 input/output blended price), it is cheaper than Hermes 3 - Llama-3.1 70B ($0.70), more expensive than Granite 4.0 H Small ($0.107).
Additional benchmarks4
Design Arena · 3d39.6%
Design Arena · Codecategories44.0%
Design Arena · Gamedev43.6%
Design Arena · Website44.8%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- DeepSeek-Coder-V2
DeepSeek · — · —
6.0——Compare - Granite 4.0 H Small
IBM · $0.107 · 14.4 t/s
6.0$0.10714.4 t/sCompare - Hermes 3 - Llama-3.1 70B
Nous Research · $0.70 · 176 t/s
6.0$0.70176 t/sCompare - Jamba 1.5 Large
AI21 Labs · $3.50 · —
6.0$3.50—Compare
