FrontierMath
FrontierMath: Measures mathematical reasoning, symbolic problem solving, proof construction, or competition-style problem solving.
2rows
scoreprimary metric
2026-05-27sampled
Metadata
Metrics
Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | GPT-5.2 | 40.3 | GPT-5.2 openai-gpt-5.2 | Imported | 2026-05-27 |
| 2 | GPT-5.5 | 35.4 | GPT-5.5 openai-gpt-5.5 | Imported | 2026-05-27 |
No matching rows.