Compare · ModelsLive · 2 picked · head to head
Claude Fable 5.1 vs Claude Sonnet 5.5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Fable 5.1 wins on 15/26 benchmarks
Claude Fable 5.1 wins 15 of 26 shared benchmarks. Leads in reasoning · knowledge · math.
Category leads
speed·Claude Sonnet 5.5agentic·Claude Sonnet 5.5reasoning·Claude Fable 5.1knowledge·Claude Fable 5.1general·Claude Sonnet 5.5coding·Claude Sonnet 5.5math·Claude Fable 5.1
Head to head · from the data · data as of 2026-11-17
- Benchmarks · Claude Fable 5.1 leads on 13 of 26 shared benchmarks (Artificial Analysis · Humanity's Last Exam, Artificial Analysis · Long Context Reasoning, Artificial Analysis · SciCode, ARC-AGI, 9 more), Claude Sonnet 5.5 on 11 (Artificial Analysis · CritPt, Artificial Analysis · GDPval, Artificial Analysis · Quality Index, APEX-Agents, 7 more) · 2 tied
- Price · Claude Fable 5.1 input $10.00/M vs Claude Sonnet 5.5 $2.00/M, Claude Sonnet 5.5 is 80% cheaper (OpenRouter list price, as of 2026-11-17)
- Cheapest provider · Claude Fable 5.1 at Amazon Bedrock and 3 other providers $10.00/M input (of 5 offers) as of 2026-11-17 · Claude Sonnet 5.5 at Amazon Bedrock and 4 other providers $2.00/M input (of 10 offers) as of 2026-11-17
- Context · Claude Fable 5.1 and Claude Sonnet 5.5 both 1.0M tokens
- Released · Claude Fable 5.1 Sep 1, 2026 vs Claude Sonnet 5.5 Sep 28, 2026 · the same month
- Price history · Claude Fable 5.1 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-17 · Claude Sonnet 5.5 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-17
Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.
Hype vs Reality
Attention vs performance
Claude Fable 5.1
#23 by perf·#7 by attention
Claude Sonnet 5.5
#18 by perf·#12 by attention
Best value
Claude Sonnet 5.5
5.2x better value than Claude Fable 5.1
Claude Fable 5.1
2.3 pts/$
$30.00/M
Claude Sonnet 5.5
11.9 pts/$
$6.00/M
Vendor risk
Who is behind the model
Anthropic
$1.40T·Tier 1
Anthropic
$1.40T·Tier 1
Head to head
26 benchmarks · 2 models
Claude Fable 5.1Claude Sonnet 5.5
Artificial Analysis · CritPt
Claude Sonnet 5.5 leads by +1.7
Claude Fable 5.1
29.7
Claude Sonnet 5.5
31.4
Artificial Analysis · GDPval
Claude Sonnet 5.5 leads by +4.2
Claude Fable 5.1
62.7
Claude Sonnet 5.5
66.9
Artificial Analysis · Humanity's Last Exam
Claude Fable 5.1 leads by +4.1
Claude Fable 5.1
59.1
Claude Sonnet 5.5
55.0
Artificial Analysis · Long Context Reasoning
Claude Fable 5.1 leads by +2.6
Claude Fable 5.1
85.3
Claude Sonnet 5.5
82.7
Artificial Analysis · Quality Index
Claude Sonnet 5.5 leads by +2.6
Claude Fable 5.1
53.4
Claude Sonnet 5.5
56.0
Artificial Analysis · SciCode
Claude Fable 5.1 leads by +2.1
Claude Fable 5.1
63.1
Claude Sonnet 5.5
61.0
APEX-Agents
Claude Sonnet 5.5 leads by +6.9
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Fable 5.1
68.6
Claude Sonnet 5.5
75.5
ARC-AGI
Claude Fable 5.1 leads by +1.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Fable 5.1
97.5
Claude Sonnet 5.5
96.5
ARC-AGI-2
Claude Fable 5.1 leads by +6.1
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Claude Fable 5.1
90.0
Claude Sonnet 5.5
83.9
Chess Puzzles
Claude Sonnet 5.5 leads by +11.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Fable 5.1
45.3
Claude Sonnet 5.5
56.9
Dtbench
Claude Fable 5.1 leads by +0.5
Claude Fable 5.1
96.0
Claude Sonnet 5.5
95.5
Frontiercode
Claude Sonnet 5.5 leads by +1.2
Claude Fable 5.1
50.9
Claude Sonnet 5.5
52.1
FrontierMath-Tier-4-v2-Private
Claude Fable 5.1 leads by +7.3
Claude Fable 5.1
87.8
Claude Sonnet 5.5
80.5
FrontierMath-Tiers-1-3-v2-Private
Claude Fable 5.1 leads by +1.5
Claude Fable 5.1
94.9
Claude Sonnet 5.5
93.4
Frontierswe
Claude Sonnet 5.5 leads by +5.6
Claude Fable 5.1
56.3
Claude Sonnet 5.5
61.9
Furniture Assembly
Claude Sonnet 5.5 leads by +7.2
Claude Fable 5.1
57.1
Claude Sonnet 5.5
64.3
HLE
Claude Fable 5.1 leads by +0.4
HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation.
Claude Fable 5.1
43.8
Claude Sonnet 5.5
43.4
Lmca
Claude Sonnet 5.5 leads by +3.3
Claude Fable 5.1
77.0
Claude Sonnet 5.5
80.3
Mirrorcode
Claude Sonnet 5.5 leads by +4.5
Claude Fable 5.1
93.3
Claude Sonnet 5.5
97.8
Mystery Game Puzzles
Claude Sonnet 5.5 leads by +7.7
Claude Fable 5.1
53.7
Claude Sonnet 5.5
61.5
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Claude Fable 5.1
100.0
Claude Sonnet 5.5
100.0
Proofbench
Claude Fable 5.1
100.0
Claude Sonnet 5.5
100.0
SimpleBench
Claude Fable 5.1 leads by +12.8
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Fable 5.1
83.9
Claude Sonnet 5.5
71.1
SimpleQA Verified
Claude Fable 5.1 leads by +24.3
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Fable 5.1
70.8
Claude Sonnet 5.5
46.5
SpireClimb
Claude Fable 5.1 leads by +0.7
Claude Fable 5.1
2.0
Claude Sonnet 5.5
1.3
WeirdML v3
Claude Fable 5.1 leads by +7.3
Claude Fable 5.1
48.4
Claude Sonnet 5.5
41.1
Full benchmark table
| Benchmark | Claude Fable 5.1 | Claude Sonnet 5.5 |
|---|---|---|
Artificial Analysis · CritPt | 29.7 | 31.4 |
Artificial Analysis · GDPval | 62.7 | 66.9 |
Artificial Analysis · Humanity's Last Exam | 59.1 | 55.0 |
Artificial Analysis · Long Context Reasoning | 85.3 | 82.7 |
Artificial Analysis · Quality Index | 53.4 | 56.0 |
Artificial Analysis · SciCode | 63.1 | 61.0 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 68.6 | 75.5 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 97.5 | 96.5 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 90.0 | 83.9 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 45.3 | 56.9 |
Dtbench | 96.0 | 95.5 |
Frontiercode | 50.9 | 52.1 |
FrontierMath-Tier-4-v2-Private | 87.8 | 80.5 |
FrontierMath-Tiers-1-3-v2-Private | 94.9 | 93.4 |
Frontierswe | 56.3 | 61.9 |
Furniture Assembly | 57.1 | 64.3 |
HLE HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation. | 43.8 | 43.4 |
Lmca | 77.0 | 80.3 |
Mirrorcode | 93.3 | 97.8 |
Mystery Game Puzzles | 53.7 | 61.5 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 100.0 | 100.0 |
Proofbench | 100.0 | 100.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 83.9 | 71.1 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 70.8 | 46.5 |
SpireClimb | 2.0 | 1.3 |
WeirdML v3 | 48.4 | 41.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $10.00 | $50.00 | 1.0M tokens (~500 books) | $200.00 | |
| $2.00 | $10.00 | 1.0M tokens (~500 books) | $40.00 |
Claude Fable 5.1 vs Claude Sonnet 5.5 · questions answered from the data
Claude Fable 5.1 leads on 13 of 26 shared benchmarks (Artificial Analysis · Humanity's Last Exam, Artificial Analysis · Long Context Reasoning, Artificial Analysis · SciCode, ARC-AGI, 9 more), Claude Sonnet 5.5 on 11 (Artificial Analysis · CritPt, Artificial Analysis · GDPval, Artificial Analysis · Quality Index, APEX-Agents, 7 more) · 2 tied
People also compared
Claude Sonnet 5.5 vs Gemini 4 CarbonClaude Fable 5.2 vs Claude Sonnet 5.5Claude Fable 5.1 vs Claude Fable 5.2Claude Sonnet 5.5 vs GPT-5 ChatClaude Sonnet 5.5 vs DeepSeek V3.2 SpecialeClaude Sonnet 5.5 vs Step 3.5 FlashClaude Sonnet 5.5 vs DeepSeek-V2 (MoE-236B, May 2024)Claude Sonnet 5.5 vs GPT-5.5 Pro