Benchmark

Frontier-Bench v0.1

Frontier-Bench v0.1 evaluates agentic terminal coding. Anthropic reports results using the mini-SWE-agent harness and a GKE backend, measured as mean…

Modality
text
Categories
agents, code
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Claude Opus 5Anthropic0.4332026-07-24evidence

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.