Alpaca, CodeAlpaca, HumanEval, LiveCodeBench, Math500, MBPP, and MT-Bench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Alpaca, CodeAlpaca, HumanEval, LiveCodeBench, Math500, MBPP, and MT-Bench
2.61Speedup (Alpaca)
8
Loading the SOTA2 catalog…