Can you release more result files from the validation leaderboard?

MMMU-Benchmark / MMMU

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

https://mmmu-benchmark.github.io/

Apache License 2.0

353 stars 24 forks source link

Closed kyleliang919 closed 6 months ago

kyleliang919 commented 6 months ago

Would be interesting to see the actual distribution of answers. Also commands to replicate those numbers?

xiangyue9607 commented 6 months ago

Sorry. We might not have the predictions for all the models as a large amount of leaderboard scores were submitted by the authors.