AI BENCHMARK PROFILE

Frontier-Bench v0.1

General AIAgents

Frontier-Bench v0.1 evaluates agentic terminal coding. Anthropic reports results using the mini-SWE-agent harness and a GKE backend, measured as mean reward across five attempts per task.

Released: Unknown
Readiness: Paper only
Primary field: General AI

Primary resources

Paper ↗

Benchmark Radar records only publicly supported details and links back to primary sources for verification.