gemma-4-31b

non-thinking, served from Oregon

Measured 2026-10-08

Build voice agents on Speko →

gemma-4-31b is measured here for comparison — it is not one of the models Speko routes.

Score

Task done

85.26%

68–100% 95% CI bootstrap over items · n=95 · measured 2026-10-08

Refusal quality

96.7%

names the gap 97% · offers a route 93% · 10 probes x 3 iterations

Fabrication

0 of 10 probes (30 probe runs) · ≤31%

Dead-air

63.7%

174 of 273 turns

Tool silence

91.0%

162 of 178 tool-call turns

Stalled

10.0%

9 of 90 runs

TTFT p50

150ms

150–158 p50–p90 · n=38

Cost / 1M tok

$1.20

Vendor list, per 1M output tokens ($0.40 in, $0.20 cached).

Share this result

Download card (PNG) Post on X

Embed the live badge

Markdown

[![Speko llm rank](https://benchmarks.speko.ai/badge/llm/hopper-gemma-4-31b.svg)](https://benchmarks.speko.ai/llm/hopper-gemma-4-31b)

HTML

<a href="https://benchmarks.speko.ai/llm/hopper-gemma-4-31b"><img src="https://benchmarks.speko.ai/badge/llm/hopper-gemma-4-31b.svg" alt="Speko llm rank"></a>

URL

https://benchmarks.speko.ai/llm/hopper-gemma-4-31b