FutureSearch BTF-3 Numeric: leaderboard
FutureSearch Bench to the Future 3 numeric-question slice scored by ranked probability score.
Metric: Numeric RPS. Source: evals.futuresearch.ai. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 (xHigh) | 0.13 | #16 (Claude Opus 5) |
| 2 | GPT-6 Astra (Low) | 0.13 | #6 (GPT-6 Astra) |
| 3 | GPT-5.6 Sol (Medium) | 0.13 | #22 (GPT-5.6 Sol) |
| 4 | Claude Opus 4.8 (xHigh) | 0.13 | #39 (Claude Opus 4.8) |
| 5 | Claude Sonnet 5 (xHigh) | 0.15 | #65 (Claude Sonnet 5) |
| 6 | Muse Spark 1.3 (xHigh) | 0.15 | #31 (Muse Spark 1.3) |
| 7 | GLM-5.3 | 0.15 | #44 |
| 8 | GLM-5.3 Flash | 0.16 | #77 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=futuresearch-btf-3-numeric · How It Works · Data refreshed daily, snapshot 2026-11-05.