Skip to content
Leaderboard / Anthropic

Claude Fable 5.1

Anthropic Max CLOSED Proprietary
Verdict

Claude Fable 5.1 is one of the very best models right now: #4 of 406 by SIscope score. Strong at everything it's been tested on, especially chat quality. On the pricey side: costs more than 99% of priced models.

SIscope score
96
#4 of 406
Human-vote rank
#4
of 419 · score 1514
Price per 1M tokens, blended
$20
$10 in · $50 out
Context window
1M
1,000,000 tokens

Shape

Each spoke is a category, 0 at the centre, 100 at the edge.

CodingAgentsReasoningMathChatInstructions

Category scores

Percentiles: 90 means better than about 90% of tested models.

Coding97
Agents & tools93
Reasoning & knowledge97
Math97
Chat quality99
Following instructions99

What goes into each category · Compare with DeepSeek V4.1 Flash

Human-vote score over time

Text arena, recent updates.

150515131520Oct 15: 1511.6 (rank #3)Oct 20: 1511.9 (rank #3)Oct 22: 1512.5 (rank #3)Oct 28: 1513.8 (rank #4)Oct 15Oct 28

Coding votes over time

WebDev arena, recent updates.

173517431750Oct 16: 1741.4 (rank #5)Oct 18: 1742.3 (rank #5)Oct 19: 1742.7 (rank #5)Oct 22: 1743.4 (rank #5)Oct 23: 1742.5 (rank #5)Oct 27: 1745 (rank #5)Oct 28: 1745.9 (rank #6)Oct 16Oct 28

Independent test runs

Run by Epoch AI on the same harness for every model. Bars show the share of questions answered correctly.

SimpleQA Verified71%
Short factual questions; rewards not making things up
Better than 95% of 100 tested models. Run Sep 1, 2026.
OTIS Mock AIME 2024-25100%
Competition maths problems in the style of AIME
Better than 96% of 313 tested models. Run Sep 1, 2026.
FrontierMath Tiers 1-390%
Very hard, unpublished research-style maths problems
Better than 97% of 122 tested models. Run Sep 1, 2026.

Human-vote arenas

People compare two anonymous answers and pick the better one. Scores work like chess ratings.

ArenaRankScoreRange (95%)VotesUpdated
Text arena
Everyday chat, blind human votes
#4 of 41915141508–152017,178Oct 28, 2026
WebDev arena
Building web apps, blind human votes
#6 of 15217461737–17548,614Oct 28, 2026
Vision arena
Questions about images, blind human votes
#4 of 16713201310–13295,026Oct 19, 2026
Agent arena
Real multi-step agent sessions
#5 of 570.1320.113–0.15017,467Nov 2, 2026

Source: Arena (formerly LMArena) leaderboard dataset, CC BY 4.0. Fetched Nov 4, 2026.

Price

Input, per 1M tokens$10Output, per 1M tokens$50Blended (3 in : 1 out)$20Context window1MSpeedComing soon

List price from the OpenRouter models API (anthropic/claude-fable-5.1), Nov 4, 2026. Providers can charge differently.