← 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

Speko llm rank
Markdown
[![Speko llm rank](https://benchmarks.speko.ai/badge/llm/inception-mercury-voice.svg)](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