Anthropic · proprietary on Arena · first on Arena 2 September 2026
claude-fable-5.1-max
26 days in first place
It held first place on Arena in Text (23 days) and WebDev (3 days).
Text: 23 days in first place
place 4 of 419 on 28 October 2026 1st10th
- On the board
- 2 September 2026 to 28 October 2026, the newest snapshot
- Score
- 1514 (1508–1520) on 28 October 2026 · 17,178 votes
- First place
-
- 2 September 2026 to 25 September 2026 · 23 days
- Catch-up
- No open-weights model has matched it in the 56 days since it first took first place.
WebDev: 3 days in first place
place 6 of 152 on 28 October 2026 1st10th
- On the board
- 2 September 2026 to 28 October 2026, the newest snapshot
- Score
- 1746 (1737–1754) on 28 October 2026 · 8,614 votes
- First place
-
- 2 September 2026 to 5 September 2026 · 3 days
- Catch-up
- No open-weights model has matched it in the 56 days since it first took first place.
Vision: best place 2
place 4 of 167 on 19 October 2026 1st10th
- On the board
- 13 September 2026 to 19 October 2026, the newest snapshot
- Score
- 1319 (1310–1329) on 19 October 2026 · 5,026 votes
Epoch AI: Claude Fable 5.1
released 1 September 2026 · API access- Chess Puzzles 48.0%
- EBR-bench 57.1%
- FrontierMath-Tier-4-v2-Private 87.8%
- FrontierMath-Tiers-1-3-v2-Private 90.2%
- Furniture Assembly 70.0%
- MirrorCode 73.3%
- Mystery Game Puzzles 58.0%
- OTIS Mock AIME 2024-2025 100.0%
- SimpleQA Verified 70.8%
- SpireClimb 2.0%
When each vendor retires it
every model’s dates- Anthropic not before 1 Sep 2027 claude-fable-5-1
- Azure AI Foundry 5 Dec 2027 claude-fable-5-1 (version 1)
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.