Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool Retrieval on G1
Loading...
95.7
Rc@50
TG
20.924
40.337
59.75
79.163
Jun 4, 2026
Rc@50
Updated 1mo ago
Evaluation Results
Method
Method
Links
Rc@50
TG
Backbone=Gemma3-4B, Tu...
2026.06
95.7
TG-3FM
Backbone=Gemma3-4B, Tu...
2026.06
95.3
TG-SP
Backbone=Gemma3-4B, St...
2026.06
94.5
TG-3FM
Backbone=Gemma3-4B, Tu...
2026.06
93
TG-5FM
Backbone=Gemma3-4B, Tu...
2026.06
92.5
TG-5FM
Backbone=Gemma3-4B, Tu...
2026.06
92.3
TG-H
Backbone=Gemma3-4B, St...
2026.06
90.8
TG
Backbone=Gemma3-4B, Tu...
2026.06
90.4
TG-5FM
Backbone=Gemma3-4B, Tu...
2026.06
48.5
TG
Backbone=Gemma3-4B, Tu...
2026.06
47
te3l
Stage=S2
2026.06
47
TG-3FM
Backbone=Gemma3-4B, Tu...
2026.06
43.1
TG-3FM
Backbone=Gemma3-4B, Tu...
2026.06
42.5
TG
Backbone=Gemma3-4B, Tu...
2026.06
38.8
TG-SP
Backbone=Gemma3-4B, St...
2026.06
38.6
TG-5FM
Backbone=Gemma3-4B, Tu...
2026.06
37.8
BM25
Stage=S2
2026.06
27.8
TG-H
Backbone=Gemma3-4B, St...
2026.06
23.8
Feedback
Search any
task
Search any
task
