RLTasksby ulam.ai
Models / Meta

Meta / MODEL EVIDENCE

Muse Wonder 1.0

6 benchmarks · 7 observations · 7 sources

Scores at a glance

6 benchmarks · large dot: Muse Wonder 1.0; small dots: closest models where reported

Closest models by score

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

20.3 percentile-point gap

4 of 6 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. HiL-Bench (Human-in-Loop Benchmark) — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  2. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  3. Humanity's Sixth Sense — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  4. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  5. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  6. SWE-Bench Pro V2 — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  7. SWE-Bench Pro V2 — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

Names used in source tables

Muse Wonder 1.0 · Muse Wonder 1.0 (max) · Muse Wonder 1.0 (mini-swe-agent) xhigh · muse-wonder-1.0