← LLM
Gemini
gemini-3.5-flash-lite
Measured 2026-10-04
Run gemini-3.5-flash-lite on Speko →One API, every model on this board.
Score
78
Task done
94.74%
79–100% 95% CI bootstrap over items · n=95 · measured 2026-10-04
Refusal quality
70.0%
names the gap 63% · offers a route 70% · 10 probes x 3 iterations · 6 silent turns scored zero
Fabrication
10%
3 of 30 probe runs
Dead-air
63.1%
173 of 274 turns
Tool silence
99.4%
173 of 174 tool-call turns
Stalled
5.6%
5 of 90 runs
TTFT p50
500ms
500–621 p50–p90 · n=38
Cost / 1M tok
$2.50
Share this result
Embed the live badge
Markdown
[](https://speko.ai/benchmarks/llm/gemini-gemini-3-5-flash-lite)
HTML
<a href="https://speko.ai/benchmarks/llm/gemini-gemini-3-5-flash-lite"><img src="https://speko.ai/benchmarks/badge/llm/gemini-gemini-3-5-flash-lite.svg" alt="Speko llm rank"></a>
URL
https://speko.ai/benchmarks/llm/gemini-gemini-3-5-flash-lite