Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scene Editing on E2A-Bench
Loading...
69.1
IF Score
Edit-As-Act
42.06
49.08
56.1
63.12
Mar 18, 2026
IF Score
SC Score
PP Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
IF Score
SC Score
PP Score
Edit-As-Act
Latency (s)=87.2, Avg....
2026.03
69.1
86.6
91.7
SceneWeaver
Latency (s)=102.5, Avg...
2026.03
68.7
78.3
82.1
Claude-4.5-opus
Latency (s)=11.3, Avg....
2026.03
50.2
43.5
68.5
GPT-5
Latency (s)=18.9, Avg....
2026.03
49.6
52.3
73.3
Gemini-3-Pro-preview
Latency (s)=47.7, Avg....
2026.03
43.1
48.7
71.7
Feedback
Search any
task
Search any
task