Hello,
I'm currently using Video-MME for multimodal video evaluation.
Since running the full benchmark locally for every model is difficult, it would be very helpful to have more official leaderboard results for comparison and validation of evaluation settings.
Could you consider adding more recent multimodal models, including Gemma 4 models, to the leaderboard?
Thank you
Hello,
I'm currently using Video-MME for multimodal video evaluation.
Since running the full benchmark locally for every model is difficult, it would be very helpful to have more official leaderboard results for comparison and validation of evaluation settings.
Could you consider adding more recent multimodal models, including Gemma 4 models, to the leaderboard?
Thank you