Qwen2.5-VL-72B-Instruct Benchmark Details

Qwen2.5-VL-72B-Instruct currently shows benchmark results led by DocVQA (1 / 5, score 96.40), MMMU (22 / 29, score 70.20).

Benchmark Results

Qwen2.5-VL-72B-Instruct

Benchmark Results

Multimodal Understanding

2 evaluations

Benchmark / mode

Score

Rank/total

96.40

1 / 5

70.20

22 / 29

Compare with other models