OpenAI

GPT-4o (Aug '24)

Aug 6, 2024Closed weightsModels.dev

Compare

Intelligence

7.7

#520 of 744Rank 520 of 744 measured models

Output speed

147 t/s

#92 of 403Rank 92 of 403 measured models

Price/1M

$4.38

#557 of 659Rank 557 of 659 measured models

Context window

128K

#773 of 1199Rank 773 of 1199 measured models

GPT-4o (Aug '24) scores 7.7 on the Artificial Analysis Intelligence Index, ranking 520th of 744 measured models. The closest models on this index are Llama 3.3 Instruct 70B (7.7), Qwen2.5 72B Instruct (7.7), and Qwen2.5 Instruct 72B (7.7). At $4.38 per million tokens (3:1 input/output blended price), it is more expensive than Llama 3.3 Instruct 70B ($0.712), Qwen2.5 72B Instruct ($0.37), and Qwen2.5 Instruct 72B ($0.48). With an output speed of 147 t/s, it is faster than Llama 3.3 Instruct 70B (92.7 t/s) and Qwen2.5 Instruct 72B (30.9 t/s).