Scale AI - EnigmaEval: leaderboard
Complex, multi-step reasoning tasks requiring models to chain together multiple inference steps to reach correct solutions.
Metric: Score. Source: scale.com. Status: years away from saturation. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Fable 5 (High) | 39.28 |
| 2 | GPT-5.6 Sol (High) | 37.12 |
| 3 | Gemini 3.1 Pro (Preview) (High) | 36.78 |
| 4 | Gemini 3.5 Flash (High) | 25.41 |
| 5 | Claude Opus 4.8 (xHigh) | 23.51 |
Interactive version: theaggregate.ai/benchmark?slug=scale-ai-enigmaeval · How It Works · Data refreshed daily, snapshot 2026-09-05.