Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Question Answering on TriviaQA (OSR%)
Loading...
12.2
OSR (%)
StepSearch-base
-0.384
2.883
6.15
9.417
Apr 19, 2026
OSR (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
OSR (%)
StepSearch-base
Backbone=Qwen2.5-3B
2026.04
12.2
StepSearch-instruct
Backbone=Qwen2.5-7B
2026.04
10.9
StepSearch-base
Backbone=Qwen2.5-7B
2026.04
7.1
Search-R1-base
Backbone=Qwen2.5-7B
2026.04
6.5
StepSearch-instruct
Backbone=Qwen2.5-3B
2026.04
4.3
Search-R1-instruct
Backbone=Qwen2.5-3B
2026.04
3.9
Search-R1-instruct
Backbone=Qwen2.5-7B
2026.04
3.9
HIPRAG-instruct
Backbone=Qwen2.5-7B
2026.04
2.2
Search-R1-base
Backbone=Qwen2.5-3B
2026.04
2.1
HIPRAG-base
Backbone=Qwen2.5-3B
2026.04
1.8
HIPRAG-instruct
Backbone=Qwen2.5-3B
2026.04
0.8
AutoSearch
Backbone=Qwen2.5-7B
2026.04
0.51
AutoSearch
Backbone=Qwen2.5-3B
2026.04
0.1
Feedback
Search any
task
Search any
task