Claude Fable 5.1
Superseded by Fable 5.2 on 2026-11-09 (OpenRouter) but has the GoBench results. GoBench lists it at $0.37 and 62 s per move in Max mode.
- Vendor
- Anthropic
- Kind
- llm
- Tier
- frontier
- Weights
- closed
- Released
- 2026-09
- Context
- 1,000k tokens
Our Go rating
Not rated yet: ratings come from tournament games against bots of known strength. See the leaderboard.
Games here
No published game yet.
Benchmarks
| Measure | Value | Unit | As of | Source |
|---|---|---|---|---|
| LMArena text (Max) | 1,503 | Elo | 2026-11 | LMArena (arena.ai) Text leaderboard, page dated 2026-11-09 |
Other games
| Measure | Value | Unit | As of | Source |
|---|---|---|---|---|
| GoBench 9x9 Track 1, no tools (Max), ±219 | 2,269 | Elo (GoBench scale) | 2026-11-03 | GoBench (Roland Gao): LLMs play full 9x9 games vs calibrated KataGo le |
| GoBench 9x9 Track 1, no tools (High), ±134 | 2,121 | Elo (GoBench scale) | 2026-11-03 | GoBench (Roland Gao): LLMs play full 9x9 games vs calibrated KataGo le |
How we run it
- untested
claude·fable— Claude Code subagent alias `fable`; which Fable version it resolves to was not verified - disallowed
openrouter·anthropic/claude-fable-5.1— PA policy (2026-11-10): Anthropic/OpenAI/Google models run through their own agents or the free key, never OpenRouter unless PA asks explicitly