OpenAI · proprietary on Arena · first on Arena 30 December 2024
o1-2024-12-17
34 days in first place
It held first place on Arena in Text (25 days) and Vision (9 days).
Text: 25 days in first place
last on the board 15 October 2026 1st10th100th
- On the board
- 30 December 2024 to 15 October 2026
- Score
- 1366 (1361–1370) on 15 October 2026 · 27,807 votes
- First place
-
- 30 December 2024 to 24 January 2025 · 25 days
- Catch-up
- Open weights matched it on 24 January 2025, 25 days after it first took first place: deepseek-r1.
Vision: 9 days in first place
last on the board 9 October 2026 1st10th100th
- On the board
- 21 February 2025 to 9 October 2026
- Score
- 1168 (1158–1179) on 9 October 2026 · 3,694 votes
- First place
-
- 11 March 2025 to 20 March 2025 · 9 days
- Catch-up
- Open weights matched it on 7 July 2025, 118 days after it first took first place: gemma-3-27b-it.
Epoch AI: o1
released 17 December 2024 · API access- Chess Puzzles 10.0%
- FrontierMath-2025-02-28-Private 9.3%
- FrontierMath-Tiers-1-3-v2-Private 14.7%
- GPQA diamond 76.8%
- MATH level 5 94.7%
- OTIS Mock AIME 2024-2025 73.3%
- SimpleQA Verified 41.1%
When each vendor retires it
every model’s dates- OpenAI 23 Oct 2026 o1-2024-12-17 · 184 days’ notice, from the notice on 22 Apr 2026
Sources
Arena scores come from people voting between two anonymous answers. First place is the highest score; the top two are often within each other’s margin of error. LMArena, Arena leaderboard dataset, revision 4491b06, retrieved 30 October 2026; Epoch AI, Capabilities & benchmarking, retrieved 30 October 2026. Both CC BY 4.0. Retirement dates: each vendor’s own deprecation page, quoted and kept, listed with the record.