RLTasksby ulam.ai
Models / Cohere

Cohere / MODEL EVIDENCE

Cohere small v20220720 (410M)

3 benchmarks · 3 observations · 3 sources

Scores at a glance

3 benchmarks · large dot: Cohere small v20220720 (410M); small dots: closest models where reported

GSM8K ↗0.4%
063.3

Cohere small v20220720 (410M) · GSM8K · EM · % ↗

HellaSwag ↗48.3%
42.982.2

Cohere small v20220720 (410M) · HellaSwag · Overall accuracy · % ↗

BoolQ ↗45.7%
089.6

Cohere small v20220720 (410M) · Accuracy ↗

Closest models by score

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

18.7 percentile-point gap

3 of 3 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. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

  2. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

  3. Holistic Evaluation of Language Models (HELM) ↗

    Stanford Center for Research on Foundation Models

Names used in source tables

Cohere small v20220720 (410M)