Claude Fable 5.1
Anthropic
The highest measured reasoning score we track.
Best reasoning
Ranked #5 of 402 on LMArena's overall board (style control) · retrieved 2026-09-19
The numbers
Arena Score (LMArena, style control)1498.5 (1490.3–1506.6, 5,783 votes)
Coding board score1518.9 (#32, 1,184 votes)
Intelligence Index (Artificial Analysis)53.4
Median output speed~69 tokens/sec
Price per 1M tokens in/out (LMArena)$10 / $50
Context window~1M
LicenseProprietary
Released2026-09-01
Exact source entries: LMArena “claude-fable-5.1-max” · Artificial Analysis “Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)”, retrieved 2026-09-19.
Try or learn moreHonest read
Best at
- Artificial Analysis Intelligence Index 53.4 — the best number we recorded on 2026-09-19
- #5 overall on LMArena (1498) with 5,783 votes
- 1,000,000-token context window
Not the pick for
- Same premium price as Fable 5 ($10 / $50) while ranking slightly lower on overall human preference
- Max-effort modes burn reasoning tokens — watch your bill
Choose it if you are
Hard analysis, mathematics and long planning chains where pure reasoning depth is the point.
Rankings come from the sources above; this plain-language read is our editorial summary of those numbers.
Compare with the leaders
Best image
Text-to-image, by blind human votes
GPT-Image 2.5 (Sunburst) · Arena Score 1421
View winner
Best video
Text-to-video, by blind human votes
Gemini Omni 1.1 Flash · Arena Score 1515
View winner
Best code
Coding, by blind human votes
Claude Fable 5 · Arena Score 1552
View winner
Best open model
Open weights, by human votes
Kimi K3 · Arena Score 1485
View winner
Best value
Intelligence per dollar
GLM 5.3 Flash · 176 pts / $1M
View winner