METR evaluation: Anthropic AI R&D acceleration is roughly twice as fast
Understand this story
After conducting a high-privilege independent evaluation of Anthropic from August 12 to October 29, 2026, METR said that as of October 2026, Anthropic's rate of model capability improvement on well-specified tasks was roughly twice that from March 2024 to October 2025, but with very high uncertainty; the true value could range from 1.3x to 3x. METR said it did not charge Anthropic for the evaluation; Anthropic only provided tokens free of charge for the evaluation, mainly for AI-assisted data analysis and visualization. METR did not request or obtain sample access to non-public models. METR also said Anthropic has unilateral rights to redact or modify all non-public information in the report.
AI overview based on source reports · Updated 11 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- METR BlogFeaturedIndependent Assessment of AI R&D Acceleration at Anthropic in October 2026
METR conducted a high-access evaluation at Anthropic from August 12 to October 29, 2026, concluding that Anthropic is likely improving model capabilities on well-specified tasks at around twice its March 2024–October 2025 rate, with AECI benchmark scores growing at an estimated 1.9x the pre-October 2025 rate (95% CI: 1.5–2.8x). METR estimates that a majority (perhaps ~80%) of the current acceleration is due to AI, found no clear bottlenecks to continued progress over the next 12 months, and cautioned that Anthropic redacted most of the evidence it found most informative.
Activity for this story
- Current comparable activity
- 6
- Peak comparable activity
- 7Nov 6 03:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.