Best video-understanding models

Models are ranked by Video-MME understanding score with current API pricing, context, and host availability. This page measures video understanding, not video-generation quality or cost-per-second output.

#ModelVideo-MMEInput $/MTokOutput $/MTokHostsContext
1Qwen2.5 VL 72B Instruct73.5$0.25$0.75532k
2GPT-4o (2024-11-20)71.9$2.50$10.002128k
3GPT-4o (2024-08-06)71.9$2.50$10.004128k
4GPT-4o-mini (2024-07-18)64.8$0.15$0.602128k
5Qwen VL Max51.3$0.52$2.081131k