Claim · reasoning

GPT-5.6 Terraon ARC-AGI-2

18.8 to 83.9 the range across every scoreable measurement we hold
65.2 points between the highest and the lowest
67.1 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 1 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.

ScoreProvenanceConfigurationWho ran itWhere to check it
83.9 / 100
as published: 83.9%
INDEPENDENT
counts toward the ranking
gpt-5.6-terra
effort max
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
74.2 / 100
as published: 74.2%
INDEPENDENT
counts toward the ranking
gpt-5.6-terra
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
67.1 / 100
as published: 67.1%
INDEPENDENT
counts toward the ranking
gpt-5.6-terra
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
37.5 / 100
as published: 37.5%
INDEPENDENT
counts toward the ranking
gpt-5.6-terra
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
18.8 / 100
as published: 18.8%
INDEPENDENT
counts toward the ranking
gpt-5.6-terra
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
← 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.