Model

Qwen3.8 Max 0902

Alibaba · open weights

qwenlm.github.io

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt17.7accuracyN/AIndependentlowepoch.ai
GPQA Diamond92.3accuracyN/AIndependenthighepoch.ai
SimpleQA Verified47.3accuracyN/AIndependenthighepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
SciCode52.1scoreN/AIndependentmediumartificialanalysis.ai
Video2World26.6v2wscoreN/AIndependentmediumarxiv.org

Safety & Alignment

Safety & Alignment
BenchmarkScoreMetricHarnessSourceConfidenceLink
Nonpublic Vulnerabilities Benchmark0.5attack_scoreopencodeIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…