← LLM
OpenAI
gpt-5.6-luna
reasoning off (required with tools)
Measured 2026-10-04
Run gpt-5.6-luna on Speko →One API, every model on this board.
Score
70
Task done
75.61%
58–91% 95% CI bootstrap over items · n=95 · measured 2026-10-04
Refusal quality
95.6%
names the gap 97% · offers a route 93% · 10 probes x 3 iterations
Fabrication
0%
0 of 10 probes (30 probe runs) · ≤31%
Dead-air
68.1%
216 of 317 turns
Tool silence
99.5%
216 of 217 tool-call turns
Stalled
25.6%
23 of 90 runs
TTFT p50
546ms
546–683 p50–p90 · n=38
Cost / 1M tok
$1.20
Share this result
Embed the live badge
Markdown
[](https://speko.ai/benchmarks/llm/openai-gpt-5-6-luna)
HTML
<a href="https://speko.ai/benchmarks/llm/openai-gpt-5-6-luna"><img src="https://speko.ai/benchmarks/badge/llm/openai-gpt-5-6-luna.svg" alt="Speko llm rank"></a>
URL
https://speko.ai/benchmarks/llm/openai-gpt-5-6-luna