←BackCLUEbenchmark/SuperCLUElyb0Copy as MarkdownView on GitHub↗144 stars·6 forks·0 viewswww.superclueai.com↗SuperCLUElybFeaturesModel Evaluation - Crowdsourced leaderboard using Elo ratings for anonymous model battles.Evaluation Benchmarks - Crowdsourced leaderboard for evaluating conversational model performance.