Model

claude-opus-4-20250514-16K

Anthropic · closed weights

anthropic.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
GPQA Diamond76.3accuracyN/AIndependenthighepoch.ai

Abstract Reasoning

Abstract Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
ARC-AGI-28.6scoreN/AIndependentlowepoch.ai

Reproduced by the community

Loading community runs…