Model

Mistral Large 3

Mistral AI · open weights

mistral.ai

Agentic / Tool Use

Agentic / Tool Use
BenchmarkScoreMetricHarnessSourceConfidenceLink
XiangqiBench0.8pass@3N/AIndependentmediumarxiv.org

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
GDP.pdf2.0gdp.pdf_scoreN/AIndependentmediumsurgehq.ai

Safety & Alignment

Safety & Alignment
BenchmarkScoreMetricHarnessSourceConfidenceLink
AgentPrivArena16.2leak_rate_(%,_↓)agentprivarenaIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…