Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Capability Evaluation Suite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Overall CapabilityCapability Evaluation Suite Aggregate
Overall Capability Score83.5
4
Mathematical ReasoningCapability Evaluation Suite Math Pool
S_Math Score69.12
4
Coding CapabilityCapability Evaluation Suite Code Pool
S_Code Score79.1
4
Commonsense ReasoningCapability Evaluation Suite Commonsense Pool
S_Com Score97.03
4
General CapabilityCapability Evaluation Suite General Pool
S_Gen Score91.61
4
Showing 5 of 5 rows