- Intelligence
- 6.3
- Rank 620 of 744 measured models
- Coding
- 3.8
- Rank 290 of 298 measured models
- Output speed
- 46.1 t/s
- Rank 329 of 403 measured models
- Price/1M
- $0.131
- Rank 118 of 659 measured models
- Context window
- 128K
- Rank 773 of 1199 measured models
Phi-4 Mini Instruct scores 6.3 on the Artificial Analysis Intelligence Index, ranking 620th of 744 measured models. The closest models on this index are Celeris-1 (6.3), EXAONE 4.0 32B (6.3), and Grok-1 (6.3). At $0.131 per million tokens (3:1 input/output blended price), it is cheaper than Celeris-1 ($0.325). With an output speed of 46.1 t/s, it is slower than Celeris-1 (1,459 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Celeris-1
Celeris · $0.325 · 1,459 t/s
6.3$0.3251,459 t/sCompare - EXAONE 4.0 32B
LG AI Research · — · —
6.3——Compare - Grok-1
SpaceXSI · — · —
6.3——Compare - Qwen2 Instruct 72B
Alibaba · — · —
6.3——Compare
