Chat turn cost
1K fresh input + 500 output tokens
Claude Fable 5.2
Claude Fable 5.2 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Claude Fable 5 vs Claude Fable 5.2
Updated November 9, 2026. Rank says Claude Fable 5.2 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty. This is a same-family comparison, so migration details appear when the source data supports them.
Share or export
Decision reading
Claude Fable 5.2 has the higher public point estimate, 91.19 versus 80.39. Their conditional score ranges overlap. These ranges do not establish rank confidence. 3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 3
- Claude Fable 5 only
- 23
- Claude Fable 5.2 only
- 27
- Like-for-like categories
- 2 / 8
Supported: Claude Fable 5 · Estimated: Claude Fable 5.2. Conditional ranges do not establish rank confidence.How the comparison works
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Claude Fable 5.2
Claude Fable 5.2 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Claude Fable 5.2
Claude Fable 5.2 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCoding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Claude Fable 5.2 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limitedAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Claude Fable 5.2 is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limitedLong documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Which one for a specific job
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
71.0Claude Fable 586.9Claude Fable 5.2
Directional only · BenchAlign v5.8
Claude Fable 5.2 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
23 Claude Fable 5 only
3 Shared
27 Claude Fable 5.2 only
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
OfficeQA ProMultimodal
Normalized gap 15.0Claude Fable 5:57.9%Claude Fable 5.2:72.9%SWE-bench ProCoding
Normalized gap 13.0Claude Fable 5:80%Claude Fable 5.2:93%
Bars run 0–100 on each benchmark’s normalized display scale
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Reasoning
Like-for-like- Claude Fable 5
- 72.1
- Supported · #14/157
- Claude Fable 5.2
- 90.7
- Supported · #1/157
- Basis
- BenchAlign v5.8 lane · 2 vs 3 public rows
- Reading
- Claude Fable 5.2 leads
Knowledge
Like-for-like- Claude Fable 5
- 80.1
- Supported · #7/179
- Claude Fable 5.2
- 97.6
- Supported · #1/179
- Basis
- BenchAlign v5.8 lane · 2 vs 3 public rows
- Reading
- Claude Fable 5.2 leads
Agentic
Directional only- Claude Fable 5
- 74.1
- Supported · #8/132
- Claude Fable 5.2
- 90.7
- Estimated · #1/132
- Basis
- BenchAlign v5.8 lane · 7 vs 8 public rows
- Reading
- Directional only
Coding
Directional only- Claude Fable 5
- 71.0
- Supported · #8/158
- Claude Fable 5.2
- 86.9
- Estimated · #1/158
- Basis
- BenchAlign v5.8 lane · 10 vs 8 public rows
- Reading
- Directional only
Multimodal
Directional only- Claude Fable 5
- 75.2
- Supported · #10/67
- Claude Fable 5.2
- 89.8
- Estimated · #1/67
- Basis
- BenchAlign v5.8 lane · 3 vs 6 public rows
- Reading
- Directional only
Multilingual
Not comparable- Claude Fable 5
- Not ranked
- Claude Fable 5.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Fable 5
- 77.1
- #67/157
- Claude Fable 5.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Fable 5
- 92.5
- Unranked · 2 rankable rows
- Claude Fable 5.2
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Fable 5 | Claude Fable 5.2 | Basis | Reading |
|---|---|---|---|---|
| Reasoning | 72.1Supported · #14/157 | 90.7Supported · #1/157 | Like-for-likeBenchAlign v5.8 lane · 2 vs 3 public rows | Claude Fable 5.2 leads |
| Knowledge | 80.1Supported · #7/179 | 97.6Supported · #1/179 | Like-for-likeBenchAlign v5.8 lane · 2 vs 3 public rows | Claude Fable 5.2 leads |
| Agentic | 74.1Supported · #8/132 | 90.7Estimated · #1/132 | Directional onlyBenchAlign v5.8 lane · 7 vs 8 public rows | Directional only |
| Coding | 71.0Supported · #8/158 | 86.9Estimated · #1/158 | Directional onlyBenchAlign v5.8 lane · 10 vs 8 public rows | Directional only |
| Multimodal | 75.2Supported · #10/67 | 89.8Estimated · #1/67 | Directional onlyBenchAlign v5.8 lane · 3 vs 6 public rows | Directional only |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 77.1#67/157 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 92.5Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Supported evidence per lane · bars run 0–100Methodology
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Claude Fable 5
- $0.035
- Fits in one request
- Claude Fable 5.2
- $0.028
- Fits in one request
Claude Fable 5.2 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Fable 5
- $0.65
- Fits in one request
- Claude Fable 5.2
- $0.52
- Fits in one request
Claude Fable 5.2 has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Claude Fable 5
- $0.9
- Fits in one request
- Claude Fable 5.2
- $0.6
- Fits in one request
Claude Fable 5.2 has the lower modeled cost
Costs use the listed standard API rates.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Fable 5Claude Fable 5.2
Context window
Maximum documented context; output-token limits may be lower.
Claude Fable 5
Claude Fable 5.2
API model ID
Claude Fable 5
claude-fable-5
Anthropic model overviewClaude Fable 5.2
claude-fable-5-2
Anthropic Claude Fable 5.2 model documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Fable 5
$1 per 1M cached input tokens
Claude API pricingClaude Fable 5.2
$0.2 per 1M cached input tokens
Claude API pricingDocumented inputs
Claude Fable 5
text, image
Anthropic model overviewClaude Fable 5.2
Documented outputs
Claude Fable 5
Claude Fable 5.2
Provider availability
Claude Fable 5
Generally Available · Claude API
Anthropic model overviewClaude Fable 5.2
Generally Available · Claude API, Claude products, AWS, Google Cloud, Microsoft Azure
Anthropic Fable 5.2 and Mythos 5.2 launchReasoning profile
Claude Fable 5
Reasoning
Claude Fable 5.2
Reasoning
Weight access
Claude Fable 5
Proprietary
Claude Fable 5.2
Proprietary
License
Claude Fable 5
Proprietary
Claude Fable 5.2
Proprietary
Release date
Claude Fable 5
2026-06-09
Claude Fable 5.2
2026-11-09
If you are choosing between sibling variants
- Deployment change
- Both entries list Anthropic as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Claude Fable 5.2 has the higher public point estimate, 91.19 versus 80.39. Their conditional score ranges overlap. These ranges do not establish rank confidence.
- Workload cost
- Repository review: $0.65 vs $0.52. Cache-heavy agent loop: $0.9 vs $0.6.
- Context tradeoff
- Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Claude Fable 5 or Claude Fable 5.2?
Claude Fable 5.2 has the higher public point estimate, 91.19 versus 80.39. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Which is better for coding, Claude Fable 5 or Claude Fable 5.2?
Claude Fable 5.2 scores higher for coding on the public lane, 86.9 to 71. Claude Fable 5.2 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which is better for agentic tasks, Claude Fable 5 or Claude Fable 5.2?
Claude Fable 5.2 scores higher for agentic tasks on the public lane, 90.7 to 74.1. Claude Fable 5.2 is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Claude Fable 5 or Claude Fable 5.2?
For the stated presets, chat costs $0.035 on Claude Fable 5 and $0.028 on Claude Fable 5.2; repository review costs $0.65 and $0.52; the cache-heavy agent loop costs $0.9 and $0.6. Costs use the listed standard API rates.
Which has the larger context window, Claude Fable 5 or Claude Fable 5.2?
Both models list the same context window, 1M.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence53 rows
Agentic
Terminal-Bench 4.1
Claude Fable 544.90%SourceClaude Fable 5.2—Not directly comparable
Terminal-Bench 3.0
Claude Fable 534.0%SourceClaude Fable 5.2—Not directly comparable
Terminal-Bench 2.1
Claude Fable 584.3%SourceClaude Fable 5.2—Not directly comparable
OSWorld-Verified
Claude Fable 585%SourceClaude Fable 5.2—Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Fable 580.5%SourceClaude Fable 5.2—Not directly comparable
ApprenticeBench
Claude Fable 534%SourceClaude Fable 5.2—Not directly comparable
MazeBench
Claude Fable 511%SourceClaude Fable 5.2—Not directly comparable
Terminal-Bench 4.0
Claude Fable 5—Claude Fable 5.267.60%SourceNot directly comparable
Terminal-Bench-Science 0.1
Claude Fable 5—Claude Fable 5.274.6%SourceNot directly comparable
AutomationBench
Claude Fable 5—Claude Fable 5.251.4%SourceNot directly comparable
OSWorld 2.1 Offline
Claude Fable 5—Claude Fable 5.289.3%SourceNot directly comparable
WANDR
Claude Fable 5—Claude Fable 5.282.1%SourceNot directly comparable
Remote Labor Index
Claude Fable 5—Claude Fable 5.241.3%SourceNot directly comparable
RoboDojo Sim
Claude Fable 5—Claude Fable 5.264.9%SourceNot directly comparable
DRACO
Claude Fable 5—Claude Fable 5.287.7%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Fable 595%SourceClaude Fable 5.2—Not directly comparable
SWE-bench Pro
Claude Fable 580%SourceClaude Fable 5.293%SourceClaude Fable 5.2 leads this result
FrontierSWE v2
Shared sourceClaude Fable 547.0%Claude Fable 5.269.9%Claude Fable 5.2 leads this result
FrontierCode 1.1 Main
Claude Fable 553.5%SourceClaude Fable 5.2—Not directly comparable
Terminal-Bench 2.1
Claude Fable 584.3%SourceClaude Fable 5.2—Not directly comparable
cursorBench31
Claude Fable 570.6%SourceClaude Fable 5.2—Not directly comparable
CursorBench 3.2
Claude Fable 570.5%SourceClaude Fable 5.2—Not directly comparable
VulcanBench v3
Claude Fable 589.5%SourceClaude Fable 5.2—Not directly comparable
LiveCodeBench (Vals)
Claude Fable 589.8%SourceClaude Fable 5.2—Not directly comparable
SWE-bench (Vals)
Claude Fable 595.0%SourceClaude Fable 5.2—Not directly comparable
SWE Multilingual
Claude Fable 5—Claude Fable 5.296.6%SourceNot directly comparable
SWE Multimodal
Claude Fable 5—Claude Fable 5.274.1%SourceNot directly comparable
DeepSWE
Claude Fable 5—Claude Fable 5.274.3%SourceNot directly comparable
ProgramBench
Claude Fable 5—Claude Fable 5.285.6%SourceNot directly comparable
FrontierCode 2.0
Claude Fable 5—Claude Fable 5.249.1%SourceNot directly comparable
CursorBench 4.0
Claude Fable 5—Claude Fable 5.260.0%SourceNot directly comparable
Reasoning
ARC-AGI-1
Claude Fable 598.50%SourceClaude Fable 5.2—Not directly comparable
ARC-AGI-2
Claude Fable 589.2%SourceClaude Fable 5.2—Not directly comparable
ARC-AGI-3
Claude Fable 5—Claude Fable 5.265.7%SourceNot directly comparable
ARC-AGI-3 Provider Adapter
Claude Fable 5—Claude Fable 5.294.90%SourceNot directly comparable
STEM Professor Bench
Claude Fable 5—Claude Fable 5.261.8%SourceNot directly comparable
Multimodal
ParseBench
Claude Fable 569.79%SourceClaude Fable 5.2—Not directly comparable
Blueprint-Bench 2
Claude Fable 538.6%SourceClaude Fable 5.2—Not directly comparable
OfficeQA Pro
Claude Fable 557.9%SourceClaude Fable 5.272.9%SourceClaude Fable 5.2 leads this result
Chartography (no tools)
Claude Fable 5—Claude Fable 5.273.4%SourceNot directly comparable
Chartography (tools)
Claude Fable 5—Claude Fable 5.291.6%SourceNot directly comparable
OfficeQA
Claude Fable 5—Claude Fable 5.283.4%SourceNot directly comparable
BenchCAD 2.1
Claude Fable 5—Claude Fable 5.275.4%SourceNot directly comparable
BenchCAD 2.1 (tools)
Claude Fable 5—Claude Fable 5.283.5%SourceNot directly comparable
Knowledge
GPQA Diamond (Vals)
Claude Fable 593.2%SourceClaude Fable 5.2—Not directly comparable
MMLU-Pro (Vals)
Claude Fable 591.5%SourceClaude Fable 5.2—Not directly comparable
HLE
Claude Fable 5—Claude Fable 5.274.2%SourceNot directly comparable
HLE w/o tools
Claude Fable 5—Claude Fable 5.273.2%SourceNot directly comparable
PhysicianBench
Claude Fable 5—Claude Fable 5.264.4%SourceNot directly comparable
Multilingual
Math
53 public results · 3 shared
Watch Claude Fable 5 vs Claude Fable 5.2
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 6,100+ subscribers.
Last updated November 9, 2026