Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-Web Reasoning on GAIA Open-web via SERPER (test)
Loading...
46.8
Pass@4
Qwen3-8B
21.736
28.243
34.75
41.257
Jun 15, 2026
Pass@4
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@4
Qwen3-8B
Sampling Method=DivIni...
2026.06
46.8
Gemma3-12B
Sampling Method=DivIni...
2026.06
45.2
Qwen3-4B
Sampling Method=DivIni...
2026.06
44.9
Qwen3-8B
Sampling Method=Standa...
2026.06
41.6
Qwen3-4B
Sampling Method=Standa...
2026.06
38.7
Gemma3-12B
Sampling Method=Standa...
2026.06
38
Gemma3-12B
Sampling Method=DivIni...
2026.06
35
Gemma3-12B
Sampling Method=Standa...
2026.06
34
Gemma3-12B
Sampling Method=DivIni...
2026.06
31.6
Qwen3-8B
Sampling Method=DivIni...
2026.06
30.2
Qwen3-4B
Sampling Method=DivIni...
2026.06
29
Qwen3-8B
Sampling Method=DivIni...
2026.06
28.2
Gemma3-12B
Sampling Method=Standa...
2026.06
28.2
Qwen3-4B
Sampling Method=DivIni...
2026.06
27.8
Qwen3-8B
Sampling Method=Standa...
2026.06
26
Qwen3-8B
Sampling Method=Standa...
2026.06
25.2
Qwen3-4B
Sampling Method=Standa...
2026.06
23.7
Qwen3-4B
Sampling Method=Standa...
2026.06
22.7
Feedback
Search any
task
Search any
task