Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Deductive Video Reasoning on VideoHolmes
Loading...
45
Accuracy
Gemini-2.5-Pro
22.744
28.522
34.3
40.078
Mar 18, 2026
Accuracy
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Average Score
Gemini-2.5-Pro
Size=-, Evaluation Fra...
2026.03
45
-
GPT-4o
Size=-, Evaluation Fra...
2026.03
42
57.8
Gemini-1.5-Pro
Size=-, Evaluation Fra...
2026.03
41.2
-
Insight-V++
Size=7B, Evaluation Fr...
2026.03
40.2
54.2
Insight-V
Size=7B, Evaluation Fr...
2026.03
38.5
52.9
Video-R1
Size=7B, Evaluation Fr...
2026.03
36.5
-
Qwen2.5-VL
Size=7B, Evaluation Fr...
2026.03
34.7
47.3
VideoChat-R1
Size=7B, Evaluation Fr...
2026.03
33
-
InternVL2.5
Size=8B, Evaluation Fr...
2026.03
23.6
-
Feedback
Search any
task
Search any
task