Interval Quality on Search-R1
36.5Hit RateClaude Sonnet 4.6
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Claude Sonnet 4.62026.05 | 36.5 | 0.154 | |
| Claude Opus 4.72026.05 | 23.1 | 0.114 | |
| GPT-5.2 Instant2026.05 | 21.4 | 0.031 | |
| Gemini 3.1 Pro Preview2026.05 | 20.7 | 0.079 | |
| Qwen3 235B2026.05 | 0 | 0 |