About Frontier-Bench
Definition and scoring
- Organisation
- Frontier-Bench
- Category
- Agents
- Version
- v0.1
- Direction
- higher is better
- Ranking use
- Reference
- Contamination risk
- Unknown
Agentic terminal coding tasks scored as mean reward over repeated attempts under a shared mini-SWE-agent harness. Every genuine source row stays tied to its exact model label, configuration, benchmark version and evaluation system. The summary chart shows one best compatible score per canonical product; Score 2.0 admits only explicitly mapped, frozen protocols and keeps incompatible configurations separate.
Open benchmark source ↗