Compare · ModelsLive · 3 picked · head to head
Claude Fable 5.2 vs Claude Opus 5.5 vs Claude Sonnet 5.5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Claude Fable 5.2 wins on 17/28 benchmarks
Claude Fable 5.2 wins 17 of 28 shared benchmarks. Leads in agentic · reasoning · knowledge.
Category leads
agentic·Claude Fable 5.2reasoning·Claude Fable 5.2knowledge·Claude Fable 5.2general·Claude Fable 5.2math·Claude Fable 5.2coding·Claude Fable 5.2speed·Claude Opus 5.5
Hype vs Reality
Attention vs performance
Claude Fable 5.2
#2 by perf·#5 by attention
Claude Opus 5.5
#11 by perf·#6 by attention
Claude Sonnet 5.5
#18 by perf·#11 by attention
Best value
Claude Sonnet 5.5
1.9x better value than Claude Opus 5.5
Claude Fable 5.2
3.5 pts/$
$24.00/M
Claude Opus 5.5
6.2 pts/$
$12.00/M
Claude Sonnet 5.5
11.9 pts/$
$6.00/M
Vendor risk
Who is behind the model
Anthropic
$965.0B·Tier 1
Anthropic
$965.0B·Tier 1
Anthropic
$965.0B·Tier 1
Head to head
28 benchmarks · 3 models
Claude Fable 5.2Claude Opus 5.5Claude Sonnet 5.5
APEX-Agents
Claude Fable 5.2 leads by +4.6
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Claude Fable 5.2
80.1
Claude Opus 5.5
73.5
Claude Sonnet 5.5
75.5
ARC-AGI
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Claude Fable 5.2
98.5
Claude Opus 5.5
98.5
Claude Sonnet 5.5
96.5
ARC-AGI-2
Claude Fable 5.2 leads by +0.4
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 5.2
93.8
Claude Opus 5.5
93.3
Claude Sonnet 5.5
83.9
Chess Puzzles
Claude Fable 5.2 leads by +12.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Claude Fable 5.2
77.9
Claude Opus 5.5
65.3
Claude Sonnet 5.5
56.9
Dtbench
Claude Fable 5.2 leads by +0.5
Claude Fable 5.2
98.7
Claude Opus 5.5
98.2
Claude Sonnet 5.5
95.5
FrontierMath-Tier-4-v2-Private
Claude Fable 5.2 leads by +5.0
Claude Fable 5.2
100.0
Claude Opus 5.5
95.0
Claude Sonnet 5.5
80.5
FrontierMath-Tiers-1-3-v2-Private
Claude Fable 5.2 leads by +4.0
Claude Fable 5.2
100.0
Claude Opus 5.5
96.0
Claude Sonnet 5.5
93.4
Frontierswe
Claude Fable 5.2 leads by +7.6
Claude Fable 5.2
69.9
Claude Opus 5.5
62.3
Claude Sonnet 5.5
61.9
Furniture Assembly
Claude Fable 5.2 leads by +9.5
Claude Fable 5.2
85.7
Claude Opus 5.5
76.2
Claude Sonnet 5.5
64.3
GPQA diamond
Claude Sonnet 5.5 leads by +2.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Claude Fable 5.2
95.7
Claude Opus 5.5
91.1
Claude Sonnet 5.5
98.0
Lmca
Claude Fable 5.2 leads by +2.8
Claude Fable 5.2
83.1
Claude Opus 5.5
80.3
Claude Sonnet 5.5
80.3
Mystery Game Puzzles
Claude Fable 5.2 leads by +20.9
Claude Fable 5.2
89.0
Claude Opus 5.5
68.0
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 5.2
99.7
Claude Opus 5.5
100.0
Claude Sonnet 5.5
100.0
Proofbench
Claude Fable 5.2
100.0
Claude Opus 5.5
100.0
Claude Sonnet 5.5
100.0
SimpleBench
Claude Fable 5.2 leads by +7.8
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Claude Fable 5.2
93.9
Claude Opus 5.5
86.1
Claude Sonnet 5.5
71.1
SimpleQA Verified
Claude Fable 5.2 leads by +21.8
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Claude Fable 5.2
94.0
Claude Opus 5.5
72.2
Claude Sonnet 5.5
46.5
SpireClimb
Claude Fable 5.2 leads by +13.8
Claude Fable 5.2
19.6
Claude Opus 5.5
5.8
Claude Sonnet 5.5
1.3
Artificial Analysis · CritPt
Claude Opus 5.5 leads by +0.3
Claude Opus 5.5
31.7
Claude Sonnet 5.5
31.4
Artificial Analysis · GDPval
Claude Opus 5.5 leads by +1.4
Claude Opus 5.5
68.3
Claude Sonnet 5.5
66.9
Artificial Analysis · Humanity's Last Exam
Claude Opus 5.5 leads by +6.4
Claude Opus 5.5
61.4
Claude Sonnet 5.5
55.0
Artificial Analysis · Long Context Reasoning
Claude Opus 5.5 leads by +2.0
Claude Opus 5.5
84.7
Claude Sonnet 5.5
82.7
Artificial Analysis · Quality Index
Claude Opus 5.5 leads by +1.6
Claude Opus 5.5
57.6
Claude Sonnet 5.5
56.0
Artificial Analysis · SciCode
Claude Opus 5.5 leads by +5.9
Claude Opus 5.5
66.9
Claude Sonnet 5.5
61.0
Ebr Bench
Claude Fable 5.2 leads by +19.0
Claude Fable 5.2
90.5
Claude Opus 5.5
71.4
Frontiercode
Claude Opus 5.5 leads by +2.5
Claude Opus 5.5
54.6
Claude Sonnet 5.5
52.1
Mirrorcode
Claude Sonnet 5.5 leads by +2.2
Claude Opus 5.5
95.6
Claude Sonnet 5.5
97.8
Remote Labor Index
Claude Fable 5.2 leads by +20.0
Claude Fable 5.2
41.3
Claude Opus 5.5
21.3
WeirdML v3
Claude Opus 5.5 leads by +14.3
Claude Opus 5.5
55.4
Claude Sonnet 5.5
41.1
Full benchmark table
| Benchmark | Claude Fable 5.2 | Claude Opus 5.5 | Claude Sonnet 5.5 |
|---|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 80.1 | 73.5 | 75.5 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 98.5 | 98.5 | 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. | 93.8 | 93.3 | 83.9 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 77.9 | 65.3 | 56.9 |
Dtbench | 98.7 | 98.2 | 95.5 |
FrontierMath-Tier-4-v2-Private | 100.0 | 95.0 | 80.5 |
FrontierMath-Tiers-1-3-v2-Private | 100.0 | 96.0 | 93.4 |
Frontierswe | 69.9 | 62.3 | 61.9 |
Furniture Assembly | 85.7 | 76.2 | 64.3 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 95.7 | 91.1 | 98.0 |
Lmca | 83.1 | 80.3 | 80.3 |
Mystery Game Puzzles | 89.0 | 68.0 | 61.5 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 99.7 | 100.0 | 100.0 |
Proofbench | 100.0 | 100.0 | 100.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 93.9 | 86.1 | 71.1 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 94.0 | 72.2 | 46.5 |
SpireClimb | 19.6 | 5.8 | 1.3 |
Artificial Analysis · CritPt | n/a | 31.7 | 31.4 |
Artificial Analysis · GDPval | n/a | 68.3 | 66.9 |
Artificial Analysis · Humanity's Last Exam | n/a | 61.4 | 55.0 |
Artificial Analysis · Long Context Reasoning | n/a | 84.7 | 82.7 |
Artificial Analysis · Quality Index | n/a | 57.6 | 56.0 |
Artificial Analysis · SciCode | n/a | 66.9 | 61.0 |
Ebr Bench | 90.5 | 71.4 | n/a |
Frontiercode | n/a | 54.6 | 52.1 |
Mirrorcode | n/a | 95.6 | 97.8 |
Remote Labor Index | 41.3 | 21.3 | n/a |
WeirdML v3 | n/a | 55.4 | 41.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $8.00 | $40.00 | 1.0M tokens (~500 books) | $160.00 | |
| $4.00 | $20.00 | 1.0M tokens (~500 books) | $80.00 | |
| $2.00 | $10.00 | 1.0M tokens (~500 books) | $40.00 |
People also compared