Anthropic ECI - September 2026 Fit (Opus 5.5 System Card): leaderboard
Anthropic's fork of the Epoch Capabilities Index (AECI): an IRT fit over public and internal benchmark results, refit on September 18, 2026 on 374 benchmarks and 732 models, with Claude Sonnet 3.5 pinned at 130 and GPT-5 at 150 (higher is better). Values from this fit are not comparable to earlier AECI releases. From Table 2.3.5.3.A of the Claude Opus 5.5 System Card (September 2026); Opus 5, Mythos 5.1 and Opus 5.5 at max effort, earlier models at their best configuration.
Metric: AECI Score. Source: www-cdn.anthropic.com. Saturation forecast: Around July 2028. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (Max) | 169.36 | #4 (Claude Opus 5.5) |
| 2 | Claude Opus 5 (Max) | 165.18 | #19 (Claude Opus 5) |
| 3 | Claude Mythos 5 | 164.49 | #21 |
| 4 | Claude Mythos Preview | 161.88 | #20 |
No result here: #5 GPT-6 Astra, #9 GPT-6.1 Sol, #10 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=anthropic-eci-september-2026-fit-opus-5-5-system-card · How It Works · Data refreshed daily, snapshot 2026-11-08.