← LLM 
Gemini
gemini-3.8-flash
Measured 2026-10-04
Run gemini-3.8-flash on Speko →One API, every model on this board.
Score
60
Task done
85.79%
71–98% 95% CI bootstrap over items · n=95 · measured 2026-10-04
Refusal quality
96.7%
names the gap 97% · offers a route 97% · 10 probes x 3 iterations
Fabrication
0%
0 of 10 probes (30 probe runs) · ≤31%
Dead-air
65.5%
190 of 290 turns
Tool silence
100.0%
all of 19 items (190 tool-call turns) · ≥82%
Stalled
13.3%
12 of 90 runs
TTFT p50
1.21s
1.21–2.90s p50–p90 · n=38
Cost / 1M tok
$3.75
Vendor list, paid tier, per 1M output tokens; rises to $7.50 on 2027-01-01.
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/gemini-gemini-3-8-flash)
HTML
<a href="https://benchmarks.speko.ai/llm/gemini-gemini-3-8-flash"><img src="https://benchmarks.speko.ai/badge/llm/gemini-gemini-3-8-flash.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/gemini-gemini-3-8-flash