EyesInAI — AI Benchmark Leaderboard

⚡Ping

Latency & availability — single-word reply

6463 ms

🧮Reasoning

Basic math reasoning — show work, give answer

7446 ms

{ }JSON Output

Structured output compliance — valid JSON with required keys

4797 ms

💻Code Gen

Python function generation with docstring

6460 ms

🚀Throughput

Token generation speed — 500-token long-form response

11184 ms

🔍Context Recall

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

2139 ms

meta/llama-4-maverick-17b-128e-instruct