Atlas

Benchmarks

← All benchmarks

ClaimBench - Direct support

Professional Work · 2026-10-20

ClaimBench claims that paraphrase a sentence of the excerpt (gold label supported). Diagnostic split.

Top models (higher is better)

ModelScore
Claude Haiku 5.5100.0
Claude Opus 5.5100.0
Claude Sonnet 5.5100.0
GPT-6.1 Sol100.0
GPT-6 Luna100.0
Loading Atlas data…