api.groq.com Benchmark Results
Benchscope records public evaluation runs for model families hosted by api.groq.com, covering multiple benchmarks. Benchscope records public evaluation runs across 1 model family hosted on api.groq.com, covering GAIA_TEXT, MMLU, GSM8K, MUSR.
About api.groq.com Endpoints
Benchmark scores from api.groq.com endpoints reflect their serving configuration, quantization, and infrastructure — not model capability in isolation. Use canonical-prompt runs for the cleanest cross-provider comparisons.
Hosted Model Families
Model families with public evaluation runs on api.groq.com: Custom.
Recent api.groq.com Runs
- api.groq.com on GAIA_TEXT: partial; 60.0%; 1047 ms p50 latency; 10 samples.
- 4router.net on MMLU: completed; 100.0%; 2748 ms p50 latency; 1 samples.
- 4router.net on MMLU: partial; 92.5%; 3192 ms p50 latency; 14,042 samples.
- api.code-relay.com on GSM8K: partial; 98.5%; 5748 ms p50 latency; 1,319 samples.
- 4router.net on MUSR: completed; 71.4%; 2985 ms p50 latency; 756 samples.
Related
- MMLU benchmark results across all providers
- MATH benchmark results across all providers
- GSM8K benchmark results across all providers
- All model families on Benchscope
- Best LLM endpoint for MMLU
- Best LLM endpoint for MATH
- Best LLM endpoint for GSM8K
- Llama 3.3 70B on Groq vs Together AI
- How benchmark results are defined and compared
Benchscope is a JavaScript app. If the interactive interface does not load, enable JavaScript or use the links above for the main public sections.