FutureSearch BTF-2 Refinement — leaderboard
Metric: Refinement. Source: evals.futuresearch.ai. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 0.08 |
| 2 | Gemini 3.1 Pro (Preview) | 0.07 |
| 3 | GPT-5.4 | 0.06 |
| 4 | Grok 4.20 | 0.04 |
Interactive version: theaggregate.ai/benchmark?slug=futuresearch-btf-2-refinement · How the rankings work · Data refreshed daily, snapshot 2026-07-22.