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 (44 / 74, score 70.20), MMMU-Pro (210 / 229, score 46.20).

Benchmark Results

Qwen2.5-VL-72B-Instruct

Benchmark Results

Visual Understanding

3 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

70.20

44 / 74

unknown

64.50

57 / 74

unknown

46.20

210 / 229

Documents & Charts

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

96.40

1 / 5

Compare with other models