Visible tradeoffsThis is a rubric-judged signal, so it is more structured than arena taste but still depends on the scoring rubric.
source
Scale Labs
metric
Pass rate (%)
judge
Rubric
direction
higher better
group id
scale_enigma_current
domain
Reasoning / math / science
What it measures vs what it misses
✓ Measures
Performance on advanced reasoning problems.
✗ Misses
Preference, price, and broad product usability.
Why this countsIt is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.Same-test ruleThis percentile only compares models inside the exact benchmark/version group shown here. It is not a universal score.What it missesIt still misses product usability, latency, and whether the model stays correct in messy real workflows.
Parsed from the public Scale Labs page for scale-enigmaeval. Reported model configuration: claude-fable-5-high. Collapse policy: highest reported score per canonical model.
Parsed from the public Scale Labs page for scale-enigmaeval. Reported model configuration: gpt-5.6-sol-high. Collapse policy: highest reported score per canonical model.
Parsed from the public Scale Labs page for scale-enigmaeval. Reported model configuration: gemini-3.1-pro-preview-high. Collapse policy: highest reported score per canonical model.
Parsed from the public Scale Labs page for scale-enigmaeval. Reported model configuration: gemini-3.5-flash-high. Collapse policy: highest reported score per canonical model.
Parsed from the public Scale Labs page for scale-enigmaeval. Reported model configuration: claude-opus-4-8-xhigh. Collapse policy: highest reported score per canonical model.