Benchmark
FrontierMath Benchmark
What is FrontierMath?
A benchmark of hundreds of original, exceptionally challenging mathematics problems crafted and vetted by expert mathematicians, covering most major branches…
- Modality
- text
- Evaluates
- math, reasoning
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 17
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/frontiermath?top_n=500
FrontierMath results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5 | OpenAI | 0.263 | 2025-08-07 | evidence |
| GPT-5 mini | OpenAI | 0.221 | 2025-08-07 | evidence |
| GPT-5 nano | OpenAI | 0.096 | 2025-08-07 | evidence |
| GPT-5.1 | OpenAI | 0.267 | 2025-11-13 | evidence |
| GPT-5.1 Instant | OpenAI | 0.267 | 2025-11-12 | evidence |
| GPT-5.1 Thinking | OpenAI | 0.267 | 2025-11-12 | evidence |
| GPT-5.2 | OpenAI | 0.403 | 2025-12-11 | evidence |
| GPT-5.4 | OpenAI | 0.476 | 2026-03-05 | evidence |
| GPT-5.5 | OpenAI | 0.354 | 2026-04-23 | evidence |
| GPT-5.5 Pro | OpenAI | 0.396 | 2026-04-23 | evidence |
| GPT-5.6 Luna | OpenAI | 0.786 | 2026-07-09 | evidence |
| GPT-5.6 Sol | OpenAI | 0.89 | 2026-07-09 | evidence |
| GPT-5.6 Terra | OpenAI | 0.849 | 2026-07-09 | evidence |
| MAI-Code-1-Flash | Microsoft | 0.063 | 2026-06-02 | evidence |
| o1 | OpenAI | 0.055 | 2024-12-17 | evidence |
| o3 | OpenAI | 0.158 | 2025-04-16 | evidence |
| o3-mini | OpenAI | 0.092 | 2025-01-30 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.