HAODONG DUAN

KennyUTC

AI & ML interests

Video Understanding; Multi-Modal Learning

Articles

Organizations

Posts 2

view post
Post
1031
OPEN VLM LEADERBOARD JUST RELEASED the FULL EVALUATION RESULTS of GPT-4o

[TL;DR]
GPT-4o shows steady progress compared to GPT-4v (0419), with a 3% improvement on the average score (68.7% -> 72.1%). GPT-4o displays stronger perception and less hallucination.

opencompass/open_vlm_leaderboard
view post
Post
2193
Open VLM Leaderboard just updated the performance of GPT-4v (20240409), the new proprietary model ranked 1st across 50+ VLMs. Compared to the pervious version (20231106), the improvements on multimodal perception and reasoning are both huge.

Check the results:
opencompass/open_vlm_leaderboard

models

None public yet

datasets

None public yet