← LLM 
OpenAI
gpt-5-mini
reasoning
Measured 2026-10-04
Run gpt-5-mini on Speko →One API, every model on this board.
Score
45
Task done
81.93%
69–94% 95% CI bootstrap over items · n=95 · measured 2026-10-04
Refusal quality
83.3%
names the gap 83% · 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
71.9%
238 of 331 turns
Tool silence
100.0%
all of 19 items (238 tool-call turns) · ≥82%
Stalled
14.4%
13 of 90 runs
TTFT p50
1.73s
1.73–5.94s p50–p90 · n=38
Cost / 1M tok
$2.00
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/openai-gpt-5-mini)
HTML
<a href="https://benchmarks.speko.ai/llm/openai-gpt-5-mini"><img src="https://benchmarks.speko.ai/badge/llm/openai-gpt-5-mini.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/openai-gpt-5-mini