Model

Qwen3.6 Max Preview

Alibaba · open weights

qwenlm.github.io

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
GPQA Diamond87.4accuracyN/AIndependenthighepoch.ai
SimpleQA Verified52.0accuracyN/AIndependenthighepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
AgentSWE2.3scoreN/AIndependentmediumarxiv.org
SWE-bench Verified76.7resolved_rateN/AIndependenthighepoch.ai

Reproduced by the community

Loading community runs…