Anthropic ECI (AECI): leaderboard
Anthropic's internal fork of the Epoch Capabilities Index, using IRT over public and internal benchmark results to track Claude capability progression.
Metric: AECI Score. Source: abstatisticalconsulting.substack.com. Saturation forecast: Around June 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos Preview | 159.2 | #4 |
| 2 | Claude Opus 4.7 | 155.1 | #49 |
| 3 | Claude Opus 4.6 | 152.1 | #63 |
| 4 | Claude Opus 4.5 | 149 | #83 |
| 5 | Claude Sonnet 4.5 | 145.3 | #142 |
| 6 | Claude Opus 4 | 141.6 | #163 |
| 7 | Claude 3.7 Sonnet | 139.2 | #249 |
| 8 | Claude 3.5 Sonnet | 132.7 | #350 |
| 9 | Claude 3 Opus | 125.7 | #571 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=anthropic-eci-aeci · How It Works · Data refreshed daily, snapshot 2026-10-20.