models · anthropic

Claude Opus 4.7

Claude Opus 4.7 — second on the reasoning leaderboard (62.8 score). Strong long-context and instruction following.

What this registry has checked

Closed. A third party reports this model and we have recorded their numbers. Nothing of our own: no weights seen, no publisher hash held. Treat every figure here as their claim.
Methodclosed-weights

What is recorded

Publisheranthropic
OriginUnited States
LicenceAnthropic-TOS
Context window1,000,000 tokens
Modalitytext+image+file->text
Pulls recorded here45,640

Reported scores

GPQA Diamond91.4
IFBench58.6
Humanity's Last Exam42.3

Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.

Elsewhere in the registry

Registry record as of 2026-10-14. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.