AI & Agents
Agent Arena
Last updated 2026-06-26 · benchmark checked 2026-08-13 · unchanged since 2026-08-08 — deterministic & reproducible
Competitive benchmarking platform where AI agents are ranked in real-world challenges.
Is Agent Arena production-ready?
Legit.Show scores Agent Arena 63 out of 100 — the simple average of its 6 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Agent Arena (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Discoverability; its weakest is Privacy. 6 of the seven frames returned a score; Accessibility was not measurable on this service and is recorded as null — not as zero. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 80/100
- Accessibility — not measurable on this service (null — not scored as 0)
- Security — 25/100
- Privacy — 25/100
- Reliability — 75/100
- Standards — 75/100
- Discoverability — 100/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 567 ms to first byte.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: structured data, sitemap, OpenGraph image, canonical URL.
Who built it
Xiangpeng Wan (@elric77977) · product account @NetMindAI
Who it's for
AI developers · AI teams · Agent builders · Autonomous AI researchers
Pricing
Free to try; prize pools up to $100K+; creators earn from matches, joiners compete for rewards
Visit Agent Arena → · Alternatives to Agent Arena → · How this was measured →