Web
gainz.fast
Last updated 2026-08-04 · benchmark measured 2026-08-04 — deterministic & reproducible
The open arena for LLM inference speed. Verified, reproducible speedups on real GPUs — NVIDIA DGX Spark GB10 and AMD Radeon AI PRO R9700, running vLLM and llama.cpp. Submit a kernel, get it benchmarked on trusted hardware, publish the gain.
83/100
Legit Benchmark — the simple average of 7 measured frames. Frames we could not measure are left out of the average, never counted as zero. Every frame is shown below with its evidence.
Is gainz.fast production-ready?
Legit.Show scores gainz.fast 83 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on gainz.fast (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 99/100
- Accessibility — 91/100
- Security — 25/100
- Privacy — 100/100
- Reliability — 75/100
- Standards — 92/100
- Discoverability — 100/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 114 ms to first byte.
- 3 of 3 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: structured data, sitemap, OpenGraph image, canonical URL.