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

Average of 9 tasks

Benchmarks

Task NameDataset NameSOTA ResultTrend
Instruction following and reasoningAverage of 9 tasks (DollyEval, VicunaEval, GSM8K, MATH, AIME2024, HumanEval, MBPP, LiveCodeBench, GPQA-D)
Average Performance31.19
9
Showing 1 of 1 rows