Claim · reasoning

GPT-5.2 (2025-12-11)on ARC-AGI-2

0.8 to 52.9 the range across every scoreable measurement we hold

52.1 points between the highest and the lowest

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

5 declared configurations, from 1 runner

All 5 scoreable measurements here come from ONE runner, so this is not a reconciliation and is not presented as one. What it shows is how far a single runner's number moves when the model is run differently.

Every measurement

5 rows, after collapsing 2 that were one measurement written twice. 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
52.9 / 100 as published: 52.9%	INDEPENDENT counts toward the ranking	gpt-5.2-2025-12-11 effort xhigh	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
43.3 / 100 as published: 43.3%	INDEPENDENT counts toward the ranking	gpt-5.2-2025-12-11 effort high	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
26.7 / 100 as published: 26.7%	INDEPENDENT counts toward the ranking	gpt-5.2-2025-12-11 effort medium	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
9.7 / 100 as published: 9.7%	INDEPENDENT counts toward the ranking	gpt-5.2-2025-12-11 effort low	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
0.8 / 100 as published: 0.8%	INDEPENDENT counts toward the ranking	gpt-5.2-2025-12-11	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.