Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Retrieval-Augmented Question Answering on ClashEval
Loading...
70
Epsilon Obey
Gemma (v3.0, 1B)
26.32
37.66
49
60.34
May 7, 2026
Epsilon Obey
Updated 2mo ago
Evaluation Results
Method
Method
Links
Epsilon Obey
Gemma (v3.0, 1B)
Full Interaction Strat...
2026.05
70
Gemma (v3.0, 1B)
Full Interaction Strat...
2026.05
57
Gemma (v3.0, 4B)
Full Interaction Strat...
2026.05
51
Qwen (v3.0, 4B)
Full Interaction Strat...
2026.05
51
Llama (v3.2, 3B)
Full Interaction Strat...
2026.05
50
Gemma (v3.0, 12B)
Full Interaction Strat...
2026.05
49
Gemma (v3.0, 4B)
Full Interaction Strat...
2026.05
49
Gemma (v3.0, 27B)
Full Interaction Strat...
2026.05
48
Llama (v3.3, 70B)
Full Interaction Strat...
2026.05
48
Llama (v3.2, 3B)
Full Interaction Strat...
2026.05
47
Qwen (v2.5, 72B)
Full Interaction Strat...
2026.05
46
Qwen (v3.0, 4B)
Full Interaction Strat...
2026.05
35
Gemma (v3.0, 12B)
Full Interaction Strat...
2026.05
34
Qwen (v2.5, 72B)
Full Interaction Strat...
2026.05
31
Llama (v3.3, 70B)
Full Interaction Strat...
2026.05
29
Gemma (v3.0, 27B)
Full Interaction Strat...
2026.05
28
Feedback
Search any
task
Search any
task