Benchmark
Frontier Science
Frontier Science is a benchmark of exceptionally challenging scientific reasoning problems spanning advanced natural-science domains, designed to test…
- Modality
- text
- Categories
- reasoning, general
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 1
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| MAI-Code-1-Flash | Microsoft | 0.582 | 2026-06-02 | 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.