ModelSpeedTest
ModelSpeedTest › Leaderboard › Gemini 3.5 Flash

Gemini 3.5 Flash speed benchmark

Google · gemini-3.5-flash · region: SEA

Independent inference-speed benchmarks for Gemini 3.5 Flash, measured through the official Google API: median output tokens per second, time to first token (TTFT), total response time and availability, refreshed every 15 minutes.

24 hours 7 days 30 days
Median tokens/sec147.3
Median TTFT1042 ms
Median total time1946 ms
Uptime48.6% (53/109)

Throughput over 7d

median tokens/sec — 135.9 to 154.6

Time to first token over 7d

median TTFT (ms) — 863 to 1324

Samples (successful): 53

Last measurement: Wed, 04 Nov 2026 00:15:54 GMT

Prompt version: v2 · max output tokens: 512 · temperature: 0

Region is the observed Cloudflare data center and is not a geographic guarantee. Measurements from different regions are never combined. See methodology.

Raw JSON for this model →