# METR finds Anthropic model benchmark scores growing 1.9x faster since October 2025

> Original title: 1. Benchmarks provide one piece of evidence for acceleration. Since Oct 2025, AECI scores for Anthropic’s models have grown at 1.9x [95%:...

- Source: METR
- Published: 2026-11-05T18:36:42.000Z
- Bad Influence: https://badinfluence.news/items/oklbzoevd0pl0bo4a19lkr8u8
- Original: https://x.com/METR_Evals/status/2118412205662314935

## Summary

METR reports that since October 2025, AECI scores for Anthropic's models have grown at 1.9x [95%: 1.5–2.8] the earlier rate. The post says analysis choices affect this estimate and that it remains unclear how benchmark scores map to real-world capabilities.

## Post

1. Benchmarks provide one piece of evidence for acceleration. Since Oct 2025, AECI scores for Anthropic’s models have grown at 1.9x [95%: 1.5–2.8] the earlier rate. Analysis choices affect this estimate, and it remains unclear how benchmark scores map to real-world capabilities.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWYbAX9b0AA-SWt.jpg&mode=thumb&exp=1794096000&sig=a4641626e4c957f1)