Project AURIONAI Use-Cases Research & Innovation
Epoch AI

Epoch Capabilities Index (ECI)

Composite that puts many benchmarks on one scale; the hub tracks 89 benchmarks

composite indexactive
2scores
2models
0independent
2maintainer-run
0vendor-reported

Definition

Version
not in the notes
Category
composite index
Maintainer
Epoch AI
Status
active
Home page
https://epoch.ai/benchmarks

Sources

  1. AI benchmarks & capabilities epoch.ai https://epoch.ai/benchmarks
  2. Claude Sonnet 5.5 erreicht Gleichstand mit Fable 5.1 im Epoch Index orcarouter.ai https://www.orcarouter.ai/de/blog/claude-sonnet-5-5-epoch-capabilities-index

Scores at a Glance

Score, Epoch AI Benchmarking Hub

Higher is better for this unit.

050100150200
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.

Scores

2 of 2 scores shown epoch-capabilities-index-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
AnthropicClaude Opus 5.5166.82 index CI 163.54 to 170.99maintainer-run–rank 1, Epoch AI Benchmarking Hub15 Oct 2026epoch.ai
OpenAIGPT-6 Astra166.41 index CI 163.35 to 171.23maintainer-runEpoch data file of 15 Oct 2026: 0.41 behind Claude Opus 5.5, within each other's confidence intervalsrank 2, Epoch AI Benchmarking Hub15 Oct 2026epoch.ai
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Epoch Capabilities Index (ECI)", https://aurion.semai.id/benchmarks/epoch-capabilities-index/, records of October 2026.