Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Discriminative Hallucination Detection on HallusionBench
Loading...
73
Accuracy
InternVL-3.5 + FINER-Tuning
31.4
42.2
53
63.8
Mar 18, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
InternVL-3.5 + FINER-Tuning
Size=8B
2026.03
73
InternVL-3.5 + FINER-Tuning
Size=14B
2026.03
71.2
InternVL-3.5
Size=8B
2026.03
71
InternVL-3.5
Size=14B
2026.03
69.5
Qwen2.5-VL + FINER-Tuning
Size=7B
2026.03
68.5
Qwen2.5-VL
Size=7B
2026.03
65.4
OmniLMM
Size=12B
2026.03
54.9
OmniLMM + RLAIF-V
Size=12B
2026.03
53.7
LLaVA-1.6 + FINER-Tuning
Size=7B
2026.03
36.3
LLaVA-1.6
Size=7B
2026.03
33
Feedback
Search any
task
Search any
task