Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Pass Rate Evaluation on ALFWorld (Interactive Agent)
Loading...
74.15
Pass@1
EARLYEXP
24.1468
37.1284
50.11
63.0916
Mar 17, 2026
Pass@1
Pass@128
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
Pass@128
EARLYEXP
Backbone=Llama3.1-8B
2026.03
74.15
95.71
GRPO-RLVR
Backbone=Llama3.1-8B
2026.03
72.5
94.29
EARLYEXP
Backbone=Qwen2.5-7B
2026.03
72.23
92.86
LEAFE
Backbone=Llama3.1-8B
2026.03
71.79
96.43
ACE
Backbone=Llama3.1-8B
2026.03
70.32
92.5
GRPO-RLVR
Backbone=Qwen2.5-7B
2026.03
69.46
91.43
LEAFE
Backbone=Qwen2.5-7B
2026.03
67.5
94.29
ACE
Backbone=Qwen2.5-7B
2026.03
66.34
89.63
BASE (NO FT)
Backbone=Llama3.1-8B
2026.03
29.82
74.29
BASE (NO FT)
Backbone=Qwen2.5-7B
2026.03
26.07
78.57
Feedback
Search any
task
Search any
task