← LLM 
OpenAI
gpt-5.4-mini
Measured 2026-10-04
Run gpt-5.4-mini on Speko →One API, every model on this board.
Score
81
Task done
91.75%
84–98% 95% CI bootstrap over items · n=95 · measured 2026-10-04
Refusal quality
82.2%
names the gap 80% · offers a route 83% · 10 probes x 3 iterations · 5 silent turns scored zero
Fabrication
0%
0 of 10 probes (30 probe runs) · ≤31%
Dead-air
62.2%
166 of 267 turns
Tool silence
99.4%
166 of 167 tool-call turns
Stalled
12.2%
11 of 90 runs
TTFT p50
390ms
390–477 p50–p90 · n=38
Cost / 1M tok
$4.50
Vendor list, standard tier, per 1M output tokens ($0.75 in).
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/openai-gpt-5-4-mini)
HTML
<a href="https://benchmarks.speko.ai/llm/openai-gpt-5-4-mini"><img src="https://benchmarks.speko.ai/badge/llm/openai-gpt-5-4-mini.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/openai-gpt-5-4-mini