Track newly released AI benchmarks and their real-world adoption momentum.
https://benchmark-radar.com ↗ HEALTH ? 65 / Stable
Track newly released AI benchmarks and their real-world adoption momentum.
https://benchmark-radar.com ↗// readme
· · ·
| # | Benchmark | Field | Public signals |
|---|---|---|---|
| 1 | CrossSWE Paper | Agentic Coding & SWE · Multilingual & Translation | 25 HF votes · 1,407 dataset downloads |
| 2 | VisSearch-Bench Paper · Code | Knowledge & Expert QA | 22 HF votes · 61 GitHub stars |
| 3 | VIPBench Paper | Speech & Audio | 510 dataset downloads |
| 4 | IdeaTaste Paper · Code | Science | 46 HF votes · 30 GitHub stars |
| 5 | Agent Money Benchmark | Agent Security & Prompt Injection · Professional & Enterprise Work | 200 dataset downloads |
| 6 | GI-TraceBench Paper | Knowledge & Expert QA · Science | 48 dataset downloads |
| 7 | TLAPS-Bench Paper · Code | Math… |