Claim · reasoning

GPT-5.2 (2025-12-11)on OTIS Mock AIME 2024-2025

62.2 to 96.1 the range across every scoreable measurement we hold
33.9 points between the highest and the lowest
93.9 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. 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
96.1 / 100
as published: 96.1%
 INDEPENDENT
counts toward the ranking
 gpt-5.2-2025-12-11
effort high		 Epoch AI
2025-12-11T20:49:15.912Z
CC-BY-4.0
NO_URL2026-08-30
benchmark leaderboard
the leaderboard for this benchmark, not a link to this row
96.1 / 100
as published: 96.1%
 INDEPENDENT
counts toward the ranking
 gpt-5.2-2025-12-11
effort xhigh		 Epoch AI
2025-12-13T15:56:00.000Z
CC-BY-4.0
NO_URL2026-08-30
benchmark leaderboard
the leaderboard for this benchmark, not a link to this row
93.9 / 100
as published: 93.9%
 INDEPENDENT
counts toward the ranking
 gpt-5.2-2025-12-11
effort medium		 Epoch AI
2025-12-11T20:49:22.447Z
CC-BY-4.0
NO_URL2026-08-30
benchmark leaderboard
the leaderboard for this benchmark, not a link to this row
78.9 / 100
as published: 78.9%
 INDEPENDENT
counts toward the ranking
 gpt-5.2-2025-12-11
effort low		 Epoch AI
2025-12-11T20:24:25.981Z
CC-BY-4.0
NO_URL2026-08-30
benchmark leaderboard
the leaderboard for this benchmark, not a link to this row
62.2 / 100
as published: 62.2%
 INDEPENDENT
counts toward the ranking
 gpt-5.2-2025-12-11
effort none		 Epoch AI
2026-07-13T17:28:07.000Z
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.