Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Vision-Language Modeling on 16 VLM benchmark suite macro-average

75.5PASS@1 Accuracy

Qwen3.5-27B

39.6248.93558.2567.565Jun 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
75.5-
2026.06
732.8
2026.06
70.94
2026.06
70.2-
2026.06
66.9-
2026.06
625.2
2026.06
56.8-
2026.06
50.39.3
2026.06
41-