FrontierMath Tiers 1–3 (v2)Benchmark scores and sources
Published result; benchmark version and evaluation conditions remain in the id and result note.
| Row | Model | Result | Normalized (0–100) | Confidence |
|---|---|---|---|---|
| 1 | GPT-5.6 Sol OpenAI | 89%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] Tier 1-3; v2Published Jul 9, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription Open source ↗ | 89.0 | 100% confidence 100 percent, Full |
| 2 | GPT-5.6 Terra OpenAI | 84.9%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] Tier 1-3; v2Published Jul 9, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription Open source ↗ | 84.9 | 100% confidence 100 percent, Full |
| 3 | GPT-5.6 Luna OpenAI | 78.6%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] Tier 1-3; v2Published Jul 9, 2026
Retrieved Oct 9, 2026 · factual citation; MIT transcription Open source ↗ | 78.6 | 100% confidence 100 percent, Full |
Results are as published by the source behind each value (hover or tap the number). Benchmark scores are shown individually for every source/variant (a model may have multiple rows), and vary by version, harness and date; the normalized column uses the method’s fixed 0–100 scales and feeds the math pillar of the SI Score.