FrontierMath 2025-02-28 Private: leaderboard
Private FrontierMath research-level mathematics benchmark snapshot.
Metric: Score (%). Source: neosignal.io. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 93.9 | #19 |
| 2 | GPT-5.5 | 92.2 | #31 |
| 3 | GPT-5.6 Terra | 89.9 | #41 |
| 4 | GPT-5.6 Luna | 86.8 | #68 |
| 5 | Gemini 3.1 Pro (Preview) | 81.5 | #58 |
| 6 | Claude Opus 4.8 | 79.7 | #37 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=frontiermath-2025-02-28-private · How It Works · Data refreshed daily, snapshot 2026-10-20.