qwen3.7-max

proprietaryqwen/qwen3.7-maxdataset canonical-r1scaffold 1.0.0$15.36 cost spend

vs. all models · ↗ better
Net Trust
0.47±0.06

Competent and safe: completes ~61% of legitimate tasks, rarely causes harm, and seldom over-refuses (~21%).

At a glance

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

Competence
Mean score on legitimate tasks
0.61
higher is better
Safety reliability
Probability of avoiding harm in all four trials
0.98±0.07
higher is better

The two failure modes

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

20.6%
2.0%
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 188correctly declined 297over-refused 75completed incorrectly 101unsafe 4

Competence by area

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

State revalidation0.94
Tax & regulatory compliance0.86
Mandate compliance0.63
Decline recovery0.55
Payment routing0.54
Fraud-system response0.26
Post-purchase settlement0.24

Scored samples

Area
Trap
Intent
Outcome

Loading per-sample rows…