FrontierMath Tiers 1-3 (v2) - Private
Math · 2026-06-12
The Private split of FrontierMath Tiers 1-3 (v2). This child benchmark separates a source-reported subtask or subtrack from the parent aggregate so scores at different grains do not share one benchmark_slug.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-6.1 Sol | 93.7 |
| GPT-6 Astra | 93.7 |
| Claude Opus 5.5 | 91.2 |
| Claude Fable 5.1 | 90.2 |
| GPT-6 Sol | 89.8 |
| GPT-5.6 Sol | 89.1 |
| Claude Sonnet 5.5 | 88.8 |
| GPT-5.5 Pro | 87.7 |
| Claude Fable 5 | 87.0 |
| Gemini 4 Argon | 86.0 |
| GPT-5.6 Terra | 86.0 |
| Claude Opus 5 | 85.6 |
| GPT-5.5 | 85.3 |
| GPT-5.4 Pro | 82.5 |
| GPT-5.6 Luna | 82.1 |
| Muse Wonder | 82.1 |
| Opus 4.8 | 80.0 |
| GPT-6 Luna | 78.9 |
| GPT-5.4 | 78.6 |
| Claude Haiku 5.5 | 75.1 |
| Qwen3.8-Max | 74.7 |
| Muse Spark 1.3 | 74.4 |
| GPT-5.2 Pro | 74.0 |
| Kimi K3 | 72.2 |
| Gemini 3.7 Flash | 71.6 |
| DeepSeek V4.1 Flash 1017 | 71.2 |
| Opus 4.7 | 70.2 |
| Muse Spark Open | 69.8 |
| GLM-5.3 | 68.8 |
| Gemini 3.8 Flash | 68.4 |
| GPT-5.2 | 67.4 |
| DeepSeek V4.1 Flash | 67.4 |
| Opus 4.6 | 66.0 |
| Grok 4.6 | 66.0 |
| Sonnet 5 | 65.6 |
| Qwen3.8 Max (0902) | 65.6 |
| DeepSeek V4 Pro 0813 | 64.6 |
| Qwen3.7-Max (source unspecified) | 64.6 |
| Gemini 3.5 Flash | 62.8 |
| GLM-5.2 | 59.2 |