EyesInAI — AI Benchmark Leaderboard

⚡Ping

Latency & availability — single-word reply

990 ms

🧮Reasoning

Basic math reasoning — show work, give answer

1378 ms

{ }JSON Output

Structured output compliance — valid JSON with required keys

1780 ms

💻Code Gen

Python function generation with docstring

1798 ms

🚀Throughput

Token generation speed — 500-token long-form response

4101 ms

🔍Context Recall

Retrieval from in-context data — 20-item list Q&A

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B