Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
User Simulation on LastFM
Loading...
31.45
F1 Score
CoARS
5.4188
12.1769
18.935
25.6931
Apr 11, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
CoARS
Backbone=Qwen3-8B
2026.04
31.45
iAgent
Backbone=GPT-5.4-mini
2026.04
26.53
AFL
Backbone=GPT-5.4-mini
2026.04
24.82
CoARS
Backbone=Qwen3-4B
2026.04
21.64
iAgent
Backbone=Qwen3-8B
2026.04
15.72
RecoWorld
Backbone=Qwen3-8B
2026.04
15.13
AFL
Backbone=Qwen3-8B
2026.04
14.1
iAgent
Backbone=Qwen3-4B
2026.04
13.56
RecoWorld
Backbone=Qwen3-4B
2026.04
12.56
Reflexion
Backbone=GPT-5.4-mini
2026.04
11.82
AFL
Backbone=Qwen3-4B
2026.04
11.46
Reflexion
Backbone=Qwen3-8B
2026.04
8.96
Reflexion
Backbone=Qwen3-4B
2026.04
6.42
Feedback
Search any
task
Search any
task
