# Scale Labs EnigmaEval (EnigmaEval)

> A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.

Canonical page: https://benchlm.ai/benchmarks/scale-enigma-eval

- Category: [Reasoning](/reasoning)
- Last updated: September 29, 2026 snapshot

## About EnigmaEval

- Year: 2026
- Tasks: 5 published rows
- Format: Published Scale leaderboard score
- Difficulty: External agent and model evaluation
- Paper: [Scale Labs leaderboard](https://labs.scale.com/leaderboard/enigma_eval)

BenchLM mirrors 5 published rows from the EnigmaEval public table captured on September 29, 2026 snapshot.

EnigmaEval is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (5 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [claude-fable-5-high](https://labs.scale.com/leaderboard/enigma_eval) | Anthropic | 39.28% |
| 2 | [gpt-5.6-sol-high](https://labs.scale.com/leaderboard/enigma_eval) | OpenAI | 37.12% |
| 3 | [gemini-3.1-pro-preview-high](https://labs.scale.com/leaderboard/enigma_eval) | Google | 36.78% |
| 4 | [gemini-3.5-flash-high](https://labs.scale.com/leaderboard/enigma_eval) | Google | 25.41% |
| 5 | [claude-opus-4-8-xhigh](https://labs.scale.com/leaderboard/enigma_eval) | Anthropic | 23.51% |

## FAQ

### What does EnigmaEval measure?

A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.

### Which model leads the published EnigmaEval snapshot?

claude-fable-5-high currently leads the published EnigmaEval snapshot with a score of 39.28%.

### How many models are evaluated on EnigmaEval?

The September 29, 2026 snapshot contains 5 AI models.

### Does EnigmaEval affect BenchLM's overall score?

Not directly. EnigmaEval is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.