search

AILab-CVC / SEED-Bench

(CVPR2024)A benchmark for evaluating Multimodal LLMs using multiple-choice questions.
Other
276 stars 8 forks source link

Reproduce the Qwen-VL SOTAs results #9

Open jinze1994 opened 10 months ago

jinze1994 commented 10 months ago

We are honored to evaluate the Qwen-VL series on your good work Seed-Bench.

Qwen-VL and Qwen-VL-Chat achieved the SOTAs on the Seed-Bench Leaderboard until now. We provide all code and steps HERE to reproduce the results.

We would appreciate it if you update these changes on your home page and pictures.

leaderboard

geyuying commented 10 months ago

Congratulations! We have updated the leaderboard in the home page. Stay tuned for more evaluation dimensions in our benchmark!

nemonameless commented 7 months ago

Have you also evaluated on SEED-Benchv2? Hope it can be updated https://github.com/QwenLM/Qwen-VL/blob/master/eval_mm/seed_bench/EVAL_SEED.md