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

Hallucination Evaluation on MMHal

4.2Score

LLaVA-OneVision-7B w/ UnifiedReward-Think

1.76642.39823.033.6618Dec 6, 2024Mar 11, 2025Jun 14, 2025Sep 17, 2025Dec 21, 2025Mar 26, 2026Jun 30, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.04
4.2-----
2026.04
4.2-----
2026.04
4.2-----
2026.04
4.1-----
2026.04
4.1-----
2026.03
4.02-----
2026.03
4.02-----
2024.12
4-----
2026.04
4-----
2026.03
3.95-----
2026.03
3.92-----
2026.04
3.9-----
2024.12
3.89-----
2026.03
3.85-----
2024.12
3.83-----
2026.06
3.83----31
2024.12
3.75-----
2026.06
3.75----30
2024.12
3.71-----
2024.12
3.7-----
2024.12
3.65-----
2024.12
3.6-----
2026.06
3.59----39
2024.12
3.55-----
2026.06
3.55----40
2026.06
3.42----40
2024.12
3.4-----
2024.12
3.33-----
2024.12
3.31-----
2026.04
3.2-----
2026.06
3.16----37
2026.06
3.14----42
2024.12
3.11-----
2026.06
3.11----39
2024.12
2.94-----
2025.07
2.76--43--
2024.12
2.75-----
2025.07
2.75--41--
2025.07
2.7--47--
2026.06
2.64----49
2026.06
2.62----53
2026.06
2.62----49
2026.06
2.55----53
2026.06
2.55----51
2026.06
2.53----52
2024.12
2.52-----
2026.06
2.5----52
2024.12
2.49-----
2026.06
2.47----51
2026.06
2.46----52
2025.07
2.45--55--
2026.06
2.39----54
2026.06
2.38----53
2026.06
2.31----54
2026.06
2.3-----
2025.07
2.27--58--
2024.12
2.25-----
2026.06
2.15----54
2026.06
2.14----65
2025.07
2.12--64--
2026.06
2.12----54
2026.06
1.86----64
2025.04
-31.970.8---
2025.04
-4052.1---
2025.04
-42.147.9---
2026.04
----4.623.9
2026.04
----3.834.7
2026.04
----4.729.9
2026.04
----4.631.6
2026.04
----4.724.3
2026.06
-----2.76
2026.06
-----2.61
2026.06
-----2.78
2026.06
-----2.45
2026.06
-----2.5
2026.06
-----2.35
2026.06
-----2.4
2026.06
-----2.15