1.Danielxu0208 / rsi_evalA lightweight Python SDK and CLI for evaluating recursive self-improvement (RSI) methods across agent benchmarks.ai-agentsbenchmarkingllm-evaluationpythonrecursive-self-improvementrsiPythonAPACHE-2.0359 total15 forks+168 starsfrom 191 · score 5.13
2.AlibabaResearch / abenchThe repository host gives no description.PythonAPACHE-2.0164 total0 forks+55 starsfrom 109 · score 4.03
3.sharkdp / hyperfineA command-line benchmarking toolcommand-linetoolbenchmarkrustcliterminalRustAPACHE-2.029K total642 forks+44 starsfrom 29,160 · score 3.81
4.google / benchmarkA microbenchmark support librarybenchmarkC++APACHE-2.011K total1.8K forks+15 starsfrom 10,485 · score 2.77
5.GoogleChrome / lighthouse-ciAutomate running Lighthouse for every commit, viewing the changes, and preventing regressionslighthousewebperfJavaScriptAPACHE-2.07.1K total729 forks+12 starsfrom 7,117 · score 2.56
6.gilnett / learned_index_labHigh-performance Piecewise Geometric Model (PGM) learned index implementation in pure Rust with strict epsilon error guaranteesRustAPACHE-2.0166 total5 forks+4 starsfrom 162 · score 1.61
7.brianfrankcooper / YCSBYahoo! Cloud Serving BenchmarkJavaAPACHE-2.05.2K total2.3K forks+1 starsfrom 5,238 · score 0.69