Model

Claude

Anthropic · closed weights

anthropic.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
SHAD0.2anomaly_score_contribution_and_llm_interpretation_qualityN/AIndependentmediumarxiv.org

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
MBPP71.4accuracyN/AIndependentmediumarxiv.org

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
AD4Edu-Bench65.6ad4edu-bench_agreementmachine annotatorIndependentmediumarxiv.org
Artisan Benchmark39.9collision_singleN/AIndependentmediumarxiv.org
STRIDE40.0acc._(%)N/AIndependentmediumarxiv.org
VisAudit63.1recovery_rateN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…