Technology · Checked 7 November 2026

METR Finds Anthropic’s AI Benchmark Progress Sped Up 1.9×

In a November 5 assessment, METR estimated that Anthropic’s model benchmark scores improved 1.9 times as fast after October 2025. The underlying cause remains uncertain.

Explore the six-scene explainer

Key takeaways

Sourced figures and status

PeriodFigure or statusSource
Internal assessment · 12 Aug–29 Oct 2026METR reviewed internal evidence and interviewed Anthropic staff.METR assessment · 2026-11-05
Benchmark trend · since Oct 20251.9× the earlier rate of score gains. The 95% confidence interval is 1.5× to 2.8×.METR assessment · 2026-11-05
Publication · 5 Nov 2026Anthropic redacted most of the evidence METR considered most informative.METR assessment · 2026-11-05

What does 1.9× measure?

METR compared the rate at which scores improved on Anthropic’s adaptation of the Epoch Capabilities Index. The estimate means about 1.9 years of gains at the earlier pace took one year at the later pace. The analysis includes unreleased models. Sparse data and how the benchmark was constructed can affect the result. Source and context.

What did researchers learn about the cause?

Interviews and surveys pointed to AI assisting researchers. METR also examined training compute and other possible drivers. It judged that AI likely accounts for most of the recent speedup, but the precise contribution remains uncertain. The Associated Press reported that Anthropic co-founder Sam McCandlish agreed that AI was speeding up research and said the size of the effect was hard to pin down. Source and context.

Charts, maps and diagrams from the explainer

Bar chart: Anthropic’s benchmark progress sped up — 1.9× the earlier pace. METR estimates that Anthropic’s AI benchmark scores improved one point nine times as fast after October twenty twenty-five, compared with the earlier trend.
Anthropic’s benchmark progress sped up — 1.9× the earlier pace METR assessment · 2026-11-05
Bar chart: The speedup estimate has a wide range — 1.5× to 2.8×. The confidence interval runs from one point five to two point eight times the earlier pace.
The speedup estimate has a wide range — 1.5× to 2.8× METR assessment · 2026-11-05
Flow diagram: METR points to AI assistance — AI helped researchers. Staff interviews and surveys suggest that AI assistance sped up research.
METR points to AI assistance — AI helped researchers METR assessment · 2026-11-05
Flow diagram: The public saw only part of the evidence — Limited public evidence. METR had access to internal benchmarks and researchers.
The public saw only part of the evidence — Limited public evidence METR assessment · 2026-11-05
Scenario diagram: A faster benchmark trend leaves open questions — Faster gains · Uncertain cause. The benchmark results point to faster improvement on measured tasks.
A faster benchmark trend leaves open questions — Faster gains · Uncertain cause METR assessment · 2026-11-05

Watch them animate in the narrated explainer

Frequently asked questions

What did METR assess?

It studied how much AI was speeding up AI research and development inside Anthropic. One finding was an estimated 1.9× increase in the rate of benchmark-score improvement.

Does the 1.9× estimate apply to all AI tasks?

The estimate concerns a particular benchmark for Anthropic models. METR says it is less certain how the trend applies to broader, less clearly defined tasks.

Sources and reporting scope

METR assessment. 2026-11-05. Primary report with the benchmark estimate, confidence interval, evidence on AI assistance and details of what Anthropic redacted.

Associated Press. 2026-11-05. Independent coverage of METR’s findings, how it obtained internal access and Anthropic’s response.

As of 7 November 2026. The 1.9× estimate compares rates of benchmark-score improvement on Anthropic’s version of the Epoch Capabilities Index (AECI). METR’s judgment about AI’s contribution is more uncertain, and Anthropic redacted much of the most informative underlying evidence.