← LLM 
Baseten
inkling
reasoning off (gateway default)
Measured 2026-08-17
* Conditional
975B total for 41B active — 211ms first token, but stalls on 70% of runs.
Score
70
Task done
53%
36–70% 95% CI · n=30
Fabrication
4%
Dead-air
54%
Tool silence
97%
Stalled
70%
TTFT p50
211ms
211–342 p50–p90
Cost / 1M tok
$4.05
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/baseten-inkling)
HTML
<a href="https://benchmarks.speko.ai/llm/baseten-inkling"><img src="https://benchmarks.speko.ai/badge/llm/baseten-inkling.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/baseten-inkling