Task Performance on Search-R1
75.8Success RateClaude Opus 4.7
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Claude Opus 4.72026.05 | 75.8 | 1.78 | |
| Claude Sonnet 4.62026.05 | 71.1 | 1.87 | |
| GPT-5.2 Instant2026.05 | 68 | 3.69 | |
| Gemini 3.1 Pro Preview2026.05 | 53.9 | 2.09 | |
| Qwen3 235B2026.05 | 35.2 | 9.94 |