- Intelligence
- 7.0
- Rank 571 of 744 measured models
- Coding
- 21.5
- Rank 218 of 298 measured models
- Output speed
- 32.3 t/s
- Rank 385 of 403 measured models
- Price/1M
- $15
- Rank 637 of 659 measured models
- Context window
- 128K
- Rank 773 of 1199 measured models
GPT-4 Turbo scores 7.0 on the Artificial Analysis Intelligence Index, ranking 571st of 744 measured models. The closest models on this index are Command A+ (7.0), Mistral Small 3.2 (7.0), and Nova Pro (7.0). At $15 per million tokens (3:1 input/output blended price), it is more expensive than Command A+ ($4.38), Mistral Small 3.2 ($0.106), and Nova Pro ($1.40). With an output speed of 32.3 t/s, it is slower than Command A+ (61.5 t/s), Mistral Small 3.2 (37 t/s), and Nova Pro (127 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Command A+
Cohere · $4.38 · 61.5 t/s
7.0$4.3861.5 t/sCompare - Mistral Small 3.2
Mistral · $0.106 · 37 t/s
7.0$0.10637 t/sCompare - Nova Pro
Amazon · $1.40 · 127 t/s
7.0$1.40127 t/sCompare - Qwen3 VL 4B (Reasoning)
Alibaba · — · —
7.0——Compare
