OpenAI
GPT-4.5 (Preview)
Closed weights
- Intelligence
- 9.6
- Rank 437 of 744 measured models
- Context window
- 128K
- Rank 773 of 1199 measured models
GPT-4.5 (Preview) scores 9.6 on the Artificial Analysis Intelligence Index, ranking 437th of 744 measured models. The closest models on this index are DeepSeek V3 0324 (9.7), Qwen3 Coder 30B A3B Instruct (9.6), and Tri-21B-think Preview (9.6).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- DeepSeek V3 0324
DeepSeek · $0.405 · 88.5 t/s
9.7+0.1$0.40588.5 t/sCompare - Ling 2.6 Flash
InclusionAI · — · —
9.7+0.1——Compare - Qwen3 Coder 30B A3B Instruct
Alibaba · $0.30 · 156 t/s
9.6$0.30156 t/sCompare - Tri-21B-think Preview
Trillion Labs · — · —
9.6——Compare
