Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination Evaluation on Hallusion
Loading...
72.97
Score
ThinkLite-VL-7B
66.3036
68.0343
69.765
71.4957
Apr 24, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
ThinkLite-VL-7B
Base MLLM=Qwen2.5-VL
2026.04
72.97
CGC-8B
Base MLLM=Qwen3-VL
2026.04
72.56
CGC-7B
Base MLLM=Qwen2.5-VL
2026.04
72.45
Qwen3-VL-8B
2026.04
71.4
MiCo-7B
Base MLLM=Qwen2.5-VL
2026.04
69.61
Qwen2.5-VL-7B
2026.04
69.5
VLAA-Thinker-7B
Base MLLM=Qwen2.5-VL
2026.04
69.08
Qwen2-VL-7B
2026.04
68.98
MM-Eureka-7B
Base MLLM=Qwen2.5-VL
2026.04
68.45
InternVL3-8B
2026.04
66.98
NoisyRollout-7B
Base MLLM=Qwen2.5-VL
2026.04
66.66
Migician-7B
Base MLLM=Qwen2-VL
2026.04
66.56
Feedback
Search any
task
Search any
task