Anthropic (Internal)

data

closed(internal coding eval/take-home exam sets, never published)

datasheet

no

license

none

access

internal-only(referenced in announcements/system cards, not distributed)

Internal proprietary coding eval sets; only narrative results are mentioned, the data is not redistributable.

• https://www.anthropic.com/news/claude-opus-4-5 recorded 2026-09-22

  "We give prospective performance engineering candidates a notoriously difficult take-home exam. We also test new models on this exam as an internal benchmark."; partner quotes reference surpassing "internal coding benchmarks". Neither the exam nor the benchmarks are published, and no license or datasheet appears anywhere on the page

Internal-only eval sets used solely by Anthropic: no external users, no downloads, and no third-party citation as a runnable standard. There is no honest external adoption signal to record, so the level is left deliberately unscored rather than guessed at.

• https://www.anthropic.com/news/claude-opus-4-5 recorded 2026-09-29

  The page says "We also test new models on this exam as an internal benchmark" and quotes "Accuracy on our internal evals improved 20%" as a partner result. Searched the body for downloads, leaderboard and usage counts for these evals: none published.

Capability is not a meaningful axis for an eval dataset, so it is left unscored. The announcement reports the model's scores rather than any capability of the eval sets themselves.

• https://www.anthropic.com/news/claude-opus-4-5 recorded 2026-09-29

  The page describes an exam used as "an internal benchmark" and reports "Claude Opus 4.5 beats Sonnet 4.5 and competition on our internal benchmarks" as model results; it publishes no feature list or row describing the eval sets. Searched the body for capability matrix, leaderboard and eval-set specification: none.