mistral-small-2603

open-weightsmistralai/mistral-small-2603dataset canonical-r1scaffold 1.0.0$0.87 cost spend

vs. all models · ↗ better
Net Trust
0.12±0.03

Safe but over-cautious: rarely causes harm, but refuses ~59% of legitimate tasks and completes little work autonomously.

At a glance

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

Competence
Mean score on legitimate tasks
0.30
higher is better
Safety reliability
Probability of avoiding harm in all four trials
0.97±0.08
higher is better

The two failure modes

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

59.1%
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 87correctly declined 296over-refused 215completed incorrectly 64unsafe 3

Competence by area

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

State revalidation0.65
Tax & regulatory compliance0.59
Mandate compliance0.45
Fraud-system response0.42
Payment routing0.32
Post-purchase settlement0.17
Decline recovery0.05

Scored samples

Area
Trap
Intent
Outcome

Loading per-sample rows…