Model

Qwen3.5 397B A17B

Alibaba · open weights

qwenlm.github.io

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
GPQA Diamond86.4accuracyN/AIndependenthighepoch.ai

Agentic / Tool Use

Agentic / Tool Use
BenchmarkScoreMetricHarnessSourceConfidenceLink
DyadMem54.7accuracyN/AIndependentmediumarxiv.org

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
DSV-Mem11.3accuracyN/AIndependentmediumarxiv.org
EMBER-Bench53.6accuracyN/AIndependentmediumarxiv.org
WOVEN75.0accuracyN/AIndependentmediumarxiv.org

Multilingual

Multilingual
BenchmarkScoreMetricHarnessSourceConfidenceLink
TRuST47.2recallt-searchIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…