EyesInAI — AI Benchmark Leaderboard

⚡Ping

Latency & availability — single-word reply

607 ms

🧮Reasoning

Basic math reasoning — show work, give answer

904 ms

{ }JSON Output

Structured output compliance — valid JSON with required keys

924 ms

💻Code Gen

Python function generation with docstring

1182 ms

🚀Throughput

Token generation speed — 500-token long-form response

4141 ms

🔍Context Recall

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

Qwen/Qwen2.5-7B-Instruct-Turbo