Model

Qwen-3-0.6B

Alibaba · open weights

qwenlm.github.io

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
LLM4Impact Dataset1.9rmsezero-shotIndependentmediumarxiv.org
OTel49.0scoreN/AIndependentmediumarxiv.org
OUC-Benchmark74.5f1N/AIndependentmediumarxiv.org
PhysicsMate0.0accuracyN/AIndependentmediumarxiv.org

Safety & Alignment

Safety & Alignment
BenchmarkScoreMetricHarnessSourceConfidenceLink
PFaithBench48.3overansN/AIndependentmediumarxiv.org

Multilingual

Multilingual
BenchmarkScoreMetricHarnessSourceConfidenceLink
sk-bench28.9scoreN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…