Model

Qwen3-235B-A22B-Thinking-2507

Alibaba · open weights

qwenlm.github.io

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
GPQA Diamond80.1accuracyN/AIndependenthighepoch.ai
PARCEL93.0accuracyN/AIndependentmediumarxiv.org
SimpleQA Verified40.4accuracyN/AIndependenthighepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
Aider Polyglot59.6percent_correctN/AIndependentmediumaider.chat
ARCS20.3ex_e2eN/AIndependentmediumarxiv.org

Abstract Reasoning

Abstract Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
ARC-AGI-21.3scoreN/AIndependentlowepoch.ai

Reproduced by the community

Loading community runs…