Groq / GPT-OSS 20B on GSM8K
Groq hosting GPT-OSS 20B on GSM8K. Completed at 5/2/2026, 2:53:32 AM. 74.0%. 531 ms p50 latency.
Run Summary
This run is completed. Benchscope recorded 100 samples with 100 completed samples. Prompt mode: canonical. Sample scope: random.
Benchmark and Endpoint
Model family: GPT-OSS 20B. Provider: Groq. Benchmark: GSM8K. Compare this run with other public runs on the same benchmark and model pages.
Related
Benchscope is a JavaScript app. If the interactive interface does not load, enable JavaScript or use the links above for the main public sections.