← LLM 
Inception
Mercury Voice
diffusion LLM
Measured 2026-10-04
Run Mercury Voice on Speko →One API, every model on this board.
Score
73
Task done
80.53%
68–91% 95% CI bootstrap over items · n=95 · measured 2026-10-04
Refusal quality
75.6%
names the gap 67% · offers a route 70% · 10 probes x 3 iterations · 3 silent turns scored zero
Fabrication
0%
0 of 10 probes (30 probe runs) · ≤31%
Dead-air
72.8%
244 of 335 turns
Tool silence
100.0%
all of 19 items (244 tool-call turns) · ≥82%
Stalled
16.7%
15 of 90 runs
TTFT p50
443ms
443–1286 p50–p90 · n=38
Cost / 1M tok
$0.75
Vendor list (promotional), per 1M output tokens ($0.20 in).
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/inception-mercury-voice)
HTML
<a href="https://benchmarks.speko.ai/llm/inception-mercury-voice"><img src="https://benchmarks.speko.ai/badge/llm/inception-mercury-voice.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/inception-mercury-voice