Evidence Retrieval on CORTEXBENCH Comparison
46Hit@5Gemini 3.1 Pro
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gemini 3.1 Pro2026.06 | 46 | 12.6 | |
| GPT-4o2026.06 | 36.6 | 33.9 | |
| DeepSeek-V4-Flash2026.06 | 30.5 | 45.5 | |
| Claude Sonnet 4.62026.06 | 29.8 | 35.7 | |
| GPT-5.42026.06 | 29.6 | 39.5 | |
| Claude Opus 4.62026.06 | 29.1 | 49.2 | |
| DeepSeek-V3.22026.06 | 28.6 | 45.2 | |
| Gemini 3 Pro2026.06 | 24.6 | 50.9 |