← LLM 
Baseten
GLM-4.7
reasoning off (gateway default)
Measured 2026-08-17
* Conditional
Quietest of the group, but ends a turn mid-task on 43.3% of runs.
Score
89
Task done
72.46%
59–85% 95% CI bootstrap over items · n=95 · measured 2026-08-25
Refusal quality
80.0%
names the gap 67% · offers a route 83% · 10 probes x 3 iterations
Fabrication
17%
5 of 30 probe runs
Dead-air
2.3%
6 of 260 turns
Tool silence
3.7%
6 of 161 tool-call turns
Stalled
43.3%
39 of 90 runs
TTFT p50
275ms
275–431 p50–p90
Cost / 1M tok
$2.20
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/llm/baseten-glm-4-7)
HTML
<a href="https://benchmarks.speko.ai/llm/baseten-glm-4-7"><img src="https://benchmarks.speko.ai/badge/llm/baseten-glm-4-7.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/baseten-glm-4-7