BlogLLM Benchmark Scores as Published, Side by Side
Anthropic ECI (AECI): Results as Published
Every result the catalog holds for Anthropic ECI (AECI): 5 models from 1 developer, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Preference and Composite RankingsMaintainer AnthropicIntroduced 2026Data version 2026103001, as of 2026-10-30
The Anthropic ECI is Anthropic's fork of Epoch AI's Epoch Capabilities Index: a statistical fit that places models and benchmarks on one capability scale from many benchmark results. The September 2026 refit covers 374 benchmarks, 7,985 observations and 732 models; Claude Opus 5.5 is scored on 43 benchmarks.
Anthropic ECI (AECI)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Opus 5.5Anthropic, released 2026-09-22 | 169.36 | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Mythos 5.1Anthropic, released 2026-09-01 | 168.12 | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Opus 5Anthropic, released 2026-07-24 | 165.18 | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Mythos 5Anthropic, released 2026-06-09 | 164.49 | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Mythos PreviewAnthropic, released 2026-04-07 | 161.88 | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.