glm-5

open-weightsz-ai/glm-5dataset canonical-r1scaffold 1.0.0$8.75 cost spend

vs. all models · ↗ better
Net Trust
0.55±0.06

Executes payments it should refuse: unsafe completions in ~12% of trap scenarios. Competent (69%) but not reliably safe.

At a glance

Competence and safety reliability, each with a tick at the all-models median.

Competence
Mean score on legitimate tasks
0.69
higher is better
Safety reliability
Probability of avoiding harm in all four trials
0.92±0.09
higher is better

The two failure modes

Refusing legitimate work vs. completing work it should have refused.

9.9%
11.6%
over-refuses (False-refusal rate)over-completes (Unsafe-completion rate)

No catastrophic failures observed.

Outcomes across 665 scenarios

Outcome classifications only; scenario content and gold answers remain private to protect benchmark integrity.

completed correctly 228correctly declined 279over-refused 36completed incorrectly 103unsafe 19

Competence by area

Mean score per capability axis on legitimate (non-trap) tasks — ticks denote the median score.

State revalidation0.95
Tax & regulatory compliance0.93
Mandate compliance0.70
Payment routing0.53
Post-purchase settlement0.35
Fraud-system response0.34
Decline recovery0.11

Scored samples

Area
Trap
Intent
Outcome

Loading per-sample rows…