Claude Fable 5.2 Max

Released2026-11-09
Price per 1M$8.00 in · $40.00 out
Overall score70.6 · rank 1
Context window1,000,000 tokens
ProviderAnthropic
WeightsProprietary
ConfigurationMax

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 70.6 1 15
Overall: Coding 68.6 3 10
Overall: Reasoning 71.1 4 12
Overall: Agentic work 68.4 3 10
Overall: Frontend 68.7 2 3
Coding 68.7 6 3
Reasoning 67.9 20 7
Math 70.5 1 4
Knowledge 79.7 1 1
Value vs price+12.624

Buzz

Posts on XAbout 9,830 a day
Mood40% positive, 15% negative
Hacker News173 mentions this week
Checked2026-11-11

Evidence

Coding 68.7 ±2.7

BenchmarkResultSourceDate
CursorBench 60.0% Epoch AI 2026-11-11
FrontierSWE 69.9% Epoch AI 2026-11-11
SciCode 67.7% Epoch AI 2026-11-11

Reasoning 67.9 ±2.6

BenchmarkResultSourceDate
ARC-AGI-2 92.5% Epoch AI 2026-11-11
ARC-AGI-2 (ARC Prize verified) 92.5% ARC Prize 2026-11-11
GPQA Diamond 93.9% Epoch AI 2026-11-06
CritPt 35.4% Epoch AI 2026-11-11
ARC-AGI-1 (ARC Prize verified) 97.5% ARC Prize 2026-11-11
ARC-AGI-1 97.5% Epoch AI 2026-11-11
ARC-AGI-3 94.9% ARC Prize 2026-11-11
Chess Puzzles 79.0% Epoch AI 2026-11-06
Mystery Game Puzzles 90.0% Epoch AI 2026-11-06

Math 70.5 ±2.4

BenchmarkResultSourceDate
FrontierMath Tiers 1-3 95.1% Epoch AI 2026-11-06
FrontierMath Tier 4 100.0% Epoch AI 2026-11-06
ProofBench 100.0% Epoch AI 2026-11-11
OTIS Mock AIME 2024-2025 99.7% Epoch AI 2026-11-06

Knowledge 79.7 ±3.0

BenchmarkResultSourceDate
SimpleQA Verified 94.0% Epoch AI 2026-11-06

Results not used in the score

BenchmarkResultSourceWhy not used
ARC-AGI-3 65.7% ARC Prize Lower duplicate run on the same benchmark

Names matched to this model

claude-fable-5-2-max

Compare Claude Fable 5.2 Max with other models