Qwen3-VL-8B-Instruct Benchmark Details

Qwen3-VL-8B-Instruct currently shows benchmark results led by DocVQA (2 / 5, score 96.10), MMMU (46 / 74, score 69.60), MMMU-Pro (208 / 229, score 47.30).

Benchmark Results

Qwen3-VL-8B-Instruct

Benchmark Results

Visual Understanding

2 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

69.60

46 / 74

Standard Mode

47.30

208 / 229

Documents & Charts

1 evaluations

Benchmark / mode

Score

Rank/total

Standard Mode

96.10

2 / 5

Agentic Development

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal Bench Hard

Standard ModeTools

2.30

229 / 244

Compare with other models