EyesInAI — AI Benchmark Leaderboard

⚡Ping

Latency & availability — single-word reply

834 ms

🧮Reasoning

Basic math reasoning — show work, give answer

fail

{ }JSON Output

Structured output compliance — valid JSON with required keys

fail

💻Code Gen

Python function generation with docstring

1457 ms

🚀Throughput

Token generation speed — 500-token long-form response

2783 ms

🔍Context Recall

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

fail

🔧Tool Use

Function/tool calling — get_weather invocation

fail

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning