RLTasksby ulam.ai
Models / Thinking Machines

Thinking Machines / MODEL EVIDENCE

Inkling Small

3 benchmarks · 3 observations · 3 sources · released 2026-07-30

Scores at a glance

46 benchmarks · large dot: Inkling Small; small dots: closest models where reported

CritPt ↗8.29%
032.29

Inkling Small · CritPt · Accuracy · % ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

7.7 percentile-point gap

34 of 40 shared benchmark comparisons

17.7 percentile-point gap

25 of 40 shared benchmark comparisons

27.0 percentile-point gap

26 of 40 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. CritPt v2 Benchmark | Artificial Analysis ↗

    Artificial Analysis

  2. EnterpriseOps-Gym-AA Benchmark | Artificial Analysis ↗

    Artificial Analysis

  3. Harvey LAB-AA v1.1 Benchmark | Artificial Analysis ↗

    Artificial Analysis

Names used in source tables

Inkling Small