Deep Research Task on DeepSearch
47Accuracy (%)DeepVerifier
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=22026.01 | 47 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=42026.01 | 45 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=52026.01 | 44 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=72026.01 | 44 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=92026.01 | 44 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=102026.01 | 44 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=62026.01 | 43 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=12026.01 | 42 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=82026.01 | 42 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=02026.01 | 41 | 3 | 6 | |
| DeepVerifierBackbone=Claude-3.7-Sonnet, # Feedback Rounds=32026.01 | 41 | 3 | 6 |