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

Generative Hallucination Mitigation on MMHal-Bench

3.49Overall Score

GPT-4V

1.47241.99622.523.0438Apr 20, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
3.4928
2026.04
2.9249
2026.04
2.6148
2026.04
2.6150
2026.04
2.5850
2026.04
2.3352
2026.04
2.1959
2026.04
2.1554
2026.04
2.1461
2026.04
2.0756
2026.04
2.0359
2026.04
1.9664
2026.04
1.5576