Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web-based Question Answering on WebQA (200 held-out questions)
Loading...
62.7
Accuracy
MAGE
33.372
40.986
48.6
56.214
May 11, 2026
Accuracy
Delta vs Strongest Baseline
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
Delta vs Strongest Baseline
MAGE
Backbone=Qwen3-8B, Jud...
2026.05
62.7
7.7
MAGE
Backbone=Qwen3-8B, Jud...
2026.05
59.6
7.7
0-shot CoT
Backbone=Qwen3-8B, Jud...
2026.05
55
-
SC10
Backbone=Qwen3-8B, Jud...
2026.05
46.5
-
8-shot
Backbone=Qwen3-8B, Jud...
2026.05
42
-
ReAct
Backbone=Qwen3-8B, Jud...
2026.05
35.5
-
Reflexion
Backbone=Qwen3-8B, Jud...
2026.05
34.5
-
Feedback
Search any
task
Search any
task