Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
User Simulation on MovieLens
Loading...
29.74
F1 Score
CoARS
7.796
13.493
19.19
24.887
Apr 11, 2026
F1 Score
Updated 5d ago
Evaluation Results
Method
Method
Links
F1 Score
CoARS
Backbone=Qwen3-8B
2026.04
29.74
iAgent
Backbone=GPT-5.4-mini
2026.04
28.84
AFL
Backbone=GPT-5.4-mini
2026.04
24.46
CoARS
Backbone=Qwen3-4B
2026.04
19.54
RecoWorld
Backbone=Qwen3-8B
2026.04
18.67
iAgent
Backbone=Qwen3-8B
2026.04
18.56
AFL
Backbone=Qwen3-8B
2026.04
16.93
Reflexion
Backbone=GPT-5.4-mini
2026.04
16.54
iAgent
Backbone=Qwen3-4B
2026.04
15.42
AFL
Backbone=Qwen3-4B
2026.04
14.45
RecoWorld
Backbone=Qwen3-4B
2026.04
14.32
Reflexion
Backbone=Qwen3-8B
2026.04
10.28
Reflexion
Backbone=Qwen3-4B
2026.04
8.64
Feedback
Search any
task
Search any
task