Gemini 3.5 Flash: 284 tok/s and IQ 55 — Fastest Smart Model

gemini 3.5 flash ranks 8th on artificial analysis by output speed at 284 tokens/second

but it scores 55 on the intelligence index – 20+ points above every model faster than it. fastest among the ones that can actually think

announced at google i/o today, it's generally available starting now

on benchmarks it beats gpt-5.5 and claude opus 4.7 on:

- mcp atlas (83.6% vs 75.3% and 79.1%)
- finance agent v2 (57.9% vs 51.8% and 51.5%)
- charxiv reasoning (84.2% vs 84.1% and 82.1%)
- mmmu-pro (83.6% vs 81.2% and 75.2%)
- toolathlon (56.5% vs 55.6% — opus had no score)

gemini 3.5 pro is coming next month