EyesInAI — AI Benchmark Leaderboard

⚡Ping

Latency & availability — single-word reply

381 ms

🧮Reasoning

Basic math reasoning — show work, give answer

606 ms

{ }JSON Output

Structured output compliance — valid JSON with required keys

5694 ms

💻Code Gen

Python function generation with docstring

1288 ms

🚀Throughput

Token generation speed — 500-token long-form response

415 ms

🔍Context Recall

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

qwen/qwen3-vl-235b-a22b-thinking