Claim · reasoning

Claude Opus 4.6on ARC-AGI-2

64.6 to 69.2 the range across every scoreable measurement we hold

4.6 points between the highest and the lowest

66.3 the number the board uses: the lower median, a real row with its own provenance

1 declared configuration, from 1 runner

All 4 scoreable measurements here come from one runner under one declared configuration, so nothing on this page explains why they differ. That is the finding.

Two measurements, one declared configuration, +4.6 points apart. 4 rows here agree on everything the record states, the system identity included, and disagree on the number: 69.2, 68.8, 66.3, 64.6. Something moved the score and no source we hold says what. The board resolves it by taking the lower median, which is a rule and not an explanation, so it is named here rather than quietly settled. This happens in 14 of 321 claim pages.

Every measurement

4 rows. Best first. the board takes the LOWER MEDIAN of the scoreable measurements, which is a real row with its own interval and provenance rather than an interpolated average. a vendor self-report is shown beside the independent numbers and is never one of them; it cannot move a rank.

Score	Provenance	Configuration	Who ran it	Where to check it
69.2 / 100 as published: 69.2%	INDEPENDENT counts toward the ranking	effort 120k	ARC Prize via Epoch AI CC-BY-4.0	NO_URL2026-08-30 benchmark leaderboard the leaderboard for this benchmark, not a link to this row
68.8 / 100 as published: 68.8%	INDEPENDENT counts toward the ranking	effort 120k	ARC Prize via Epoch AI CC-BY-4.0	NO_URL2026-08-30 benchmark leaderboard the leaderboard for this benchmark, not a link to this row
66.3 / 100 as published: 66.3%	INDEPENDENT counts toward the ranking	effort 120k	ARC Prize via Epoch AI CC-BY-4.0	NO_URL2026-08-30 benchmark leaderboard the leaderboard for this benchmark, not a link to this row
64.6 / 100 as published: 64.6%	INDEPENDENT counts toward the ranking	effort 120k	ARC Prize via Epoch AI CC-BY-4.0	NO_URL2026-08-30 benchmark leaderboard the leaderboard for this benchmark, not a link to this row

← The Forge Rankings

Snapshot 2026-08-30-62e4e85f043b, manifest dc46131315046f1e, as of 2026-08-30. where only one party has measured a model on a benchmark, this page says so rather than presenting a single number as a reconciliation.