← LLM 
OpenAI
gpt-5.6-terra
reasoning off (required with tools)
Measured 2026-10-04
Run gpt-5.6-terra on Speko →One API, every model on this board.
Score
73
Task done
83.51%
68–96% 95% CI bootstrap over items · n=95 · measured 2026-10-04
Refusal quality
88.9%
names the gap 90% · offers a route 87% · 10 probes x 3 iterations · 1 silent turn scored zero
Fabrication
0%
0 of 10 probes (30 probe runs) · ≤31%
Dead-air
64.0%
181 of 283 turns
Tool silence
98.9%
181 of 183 tool-call turns
Stalled
21.1%
19 of 90 runs
TTFT p50
580ms
580–731 p50–p90 · n=38
Cost / 1M tok
$12.00
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/openai-gpt-5-6-terra)
HTML
<a href="https://benchmarks.speko.ai/llm/openai-gpt-5-6-terra"><img src="https://benchmarks.speko.ai/badge/llm/openai-gpt-5-6-terra.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/openai-gpt-5-6-terra