Explore benchmarks from NVIDIA Research. Find evaluation tasks, understand scoring methods, and access results and submission guidance.
Choose a benchmark to explore its tasks, methodology, and results.
Evaluate GPU kernels against theoretical hardware performance limits. SOL-ExecBench runs submissions on NVIDIA B200 GPUs and reports a Speed-of-Light (SOL) Score to help assess optimization headroom.
Evaluate coding agents on 53 SGLang tasks covering model integration, serving APIs, cache systems, and GPU kernels. Compare task success with inference cost, agent steps, and wall time. Hidden tests check behavior, including live model serving.
Check task coverage, access requirements, and scoring rules before comparing results.
Use SOL-ExecBench to evaluate GPU kernel performance on NVIDIA B200 hardware. Use SWE-Serve to evaluate coding agents on SGLang inference engineering tasks. Check that the tasks, hardware, and scoring method match your research question.
Open SOL-ExecBench to browse its Problems and Leaderboard sections. Its introduction explains the SOL Score. SWE-Serve includes a leaderboard, efficiency comparisons, and an explanation of task construction and closed-book evaluation. ```
SOL-ExecBench requires an NVIDIA account to submit solutions and track your progress. You can browse its public benchmark information and leaderboards without signing in.
Compare results under the same tasks, hardware, evaluation version, and scoring rules. Read the benchmark methodology before interpreting a score; results from different benchmarks are not directly interchangeable.
