FutureSearch DRB - Gather Evidence — leaderboard
Metric: Average Score. Source: evals.futuresearch.ai. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4 | 0.4 |
| 2 | GPT-5 | 0.38 |
| 3 | O3 | 0.38 |
| 4 | Gemini 3 Pro | 0.36 |
| 5 | Claude Opus 4.1 | 0.36 |
| 6 | Claude Sonnet 4 | 0.34 |
| 7 | Grok 4 | 0.34 |
| 8 | Claude Sonnet 4.6 | 0.33 |
| 9 | GPT-5.1 | 0.33 |
| 10 | Claude Opus 4.5 | 0.32 |
| 11 | Claude Opus 4.6 | 0.32 |
| 12 | Gemini 3 Flash | 0.3 |
| 13 | Claude Haiku 4.5 | 0.29 |
| 14 | Gemini 2.5 Pro | 0.28 |
| 15 | Claude Sonnet 4.5 | 0.28 |
Interactive version: theaggregate.ai/benchmark?slug=futuresearch-drb-gather-evidence · How the rankings work · Data refreshed daily, snapshot 2026-07-22.