RLTasksby ulam.ai
Models / Anthropic

Anthropic / MODEL EVIDENCE

Claude 3.5 Sonnet Latest

10 benchmarks · 11 observations · 11 sources

Scores at a glance

10 benchmarks · large dot: Claude 3.5 Sonnet Latest; small dots: closest models where reported

MATH-500 ↗72.4 %
25.496.4

Claude 3.5 Sonnet Latest · MATH 500 · Accuracy ↗

MMLU-Pro ↗78.4 %
30.2892.38

Claude 3.5 Sonnet Latest · MMLU Pro · Accuracy ↗

MMMU-Pro ↗68.8 %
22.7790.64

Claude 3.5 Sonnet Latest · MMMU Pro · Accuracy ↗

Closest models by score

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

9.8 percentile-point gap

7 of 10 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. AIME — evaluation methodology and results ↗

    Vals AI · 2026

  2. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  3. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

  4. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  5. MATH 500 — evaluation methodology and results ↗

    Vals AI · 2026

  6. MedQA — evaluation methodology and results ↗

    Vals AI · 2026

  7. MGSM — evaluation methodology and results ↗

    Vals AI · 2026

  8. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  9. MMMU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  10. MortgageTax — evaluation methodology and results ↗

    Vals AI · 2026

  11. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Claude 3.5 Sonnet Latest