List your company

ResearchFormerly WizWand

MT-Eval

Benchmarks

TaskDatasetSOTA resultTrendResults

Multi-turn dialogue

MT-Eval

8.16LLM-EVAL Score

20

Multi-turn Instruction Following

MT-Eval

93.62CSR

20

Multi-turn dialogue evaluation

MT-Eval

7.34Expansion Score

9

Multi-turn conversation

MT-Eval

8.28Accuracy

9

Structured Reasoning and Evaluation

MT-Eval

95.56CSR

8