Chat turn cost
1K fresh input + 500 output tokens
Muse Wonder
Muse Wonder has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Claude Fable 5.2 vs Muse Wonder
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.
Share or export
Decision reading
Claude Fable 5.2 has the higher public point estimate, 91.19 versus 63. 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 5.2 only
- 27
- Muse Wonder only
- 9
- Like-for-like categories
- 2 / 8
Estimated: Claude Fable 5.2 and Muse Wonder. 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
Muse Wonder
Muse Wonder 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
Muse Wonder
Muse Wonder 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
Muse Wonder is not ranked on the public lane for agentic, so no winner is named for agentic.
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.
86.9Claude Fable 5.265.5Muse Wonder
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.
27 Claude Fable 5.2 only
3 Shared
9 Muse Wonder only
1 category rests 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.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
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 5.2
- 90.7
- Supported · #1/157
- Muse Wonder
- 69.3
- Supported · #17/157
- Basis
- BenchAlign v5.8 lane · 3 vs 1 public rows
- Reading
- Claude Fable 5.2 leads
Knowledge
Like-for-like- Claude Fable 5.2
- 97.6
- Supported · #1/179
- Muse Wonder
- 68.3
- Supported · #19/179
- Basis
- BenchAlign v5.8 lane · 3 vs 1 public rows
- Reading
- Claude Fable 5.2 leads
Coding
Directional only- Claude Fable 5.2
- 86.9
- Estimated · #1/158
- Muse Wonder
- 65.5
- Supported · #13/158
- Basis
- BenchAlign v5.8 lane · 8 vs 5 public rows
- Reading
- Directional only
Agentic
Not comparable- Claude Fable 5.2
- 90.7
- Estimated · #1/132
- Muse Wonder
- Not ranked
- Basis
- BenchAlign v5.8 lane · 8 vs 5 public rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude Fable 5.2
- 89.8
- Estimated · #1/67
- Muse Wonder
- Not ranked
- Basis
- BenchAlign v5.8 lane · 6 vs 0 public rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Fable 5.2
- Not ranked
- Muse Wonder
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Fable 5.2
- Not ranked
- Muse Wonder
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Fable 5.2
- Not ranked
- Muse Wonder
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Fable 5.2 | Muse Wonder | Basis | Reading |
|---|---|---|---|---|
| Reasoning | 90.7Supported · #1/157 | 69.3Supported · #17/157 | Like-for-likeBenchAlign v5.8 lane · 3 vs 1 public rows | Claude Fable 5.2 leads |
| Knowledge | 97.6Supported · #1/179 | 68.3Supported · #19/179 | Like-for-likeBenchAlign v5.8 lane · 3 vs 1 public rows | Claude Fable 5.2 leads |
| Coding | 86.9Estimated · #1/158 | 65.5Supported · #13/158 | Directional onlyBenchAlign v5.8 lane · 8 vs 5 public rows | Directional only |
| Agentic | 90.7Estimated · #1/132 | Not ranked | Not comparableBenchAlign v5.8 lane · 8 vs 5 public rows | Not comparable |
| Multimodal | 89.8Estimated · #1/67 | Not ranked | Not comparableBenchAlign v5.8 lane · 6 vs 0 public rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableProvisional lane · 0 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 5.2
- $0.028
- Fits in one request
- Muse Wonder
- $0.014
- Fits in one request
Muse Wonder has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Fable 5.2
- $0.52
- Fits in one request
- Muse Wonder
- $0.26
- Fits in one request
Muse Wonder 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 5.2
- $0.6
- Fits in one request
- Muse Wonder
- $0.32
- Fits in one request
Muse Wonder 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 5.2Muse Wonder
Context window
Maximum documented context; output-token limits may be lower.
Claude Fable 5.2
Muse Wonder
API model ID
Claude Fable 5.2
claude-fable-5-2
Anthropic Claude Fable 5.2 model documentationMuse Wonder
muse-wonder-1.0
Meta: Muse Wonder models and pricingCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Fable 5.2
$0.2 per 1M cached input tokens
Claude API pricingMuse Wonder
$0.2 per 1M cached input tokens
Meta: Muse Wonder models and pricingDocumented inputs
Claude Fable 5.2
Muse Wonder
Not sourced
Documented outputs
Claude Fable 5.2
Muse Wonder
Not sourced
Provider availability
Claude Fable 5.2
Generally Available · Claude API, Claude products, AWS, Google Cloud, Microsoft Azure
Anthropic Fable 5.2 and Mythos 5.2 launchMuse Wonder
Not sourced
Reasoning profile
Claude Fable 5.2
Reasoning
Muse Wonder
Reasoning
Weight access
Claude Fable 5.2
Proprietary
Muse Wonder
Proprietary
License
Claude Fable 5.2
Proprietary
Muse Wonder
Proprietary
Release date
Claude Fable 5.2
2026-11-09
Muse Wonder
2026-10-12
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Claude Fable 5.2 has the higher public point estimate, 91.19 versus 63. Their conditional score ranges overlap. These ranges do not establish rank confidence.
- Workload cost
- Repository review: $0.52 vs $0.26. Cache-heavy agent loop: $0.6 vs $0.32.
- Context tradeoff
- Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Claude Fable 5.2 or Muse Wonder?
Claude Fable 5.2 has the higher public point estimate, 91.19 versus 63. 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 5.2 or Muse Wonder?
Claude Fable 5.2 scores higher for coding on the public lane, 86.9 to 65.5. 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 5.2 or Muse Wonder?
Muse Wonder is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.
Which costs less, Claude Fable 5.2 or Muse Wonder?
For the stated presets, chat costs $0.028 on Claude Fable 5.2 and $0.014 on Muse Wonder; repository review costs $0.52 and $0.26; the cache-heavy agent loop costs $0.6 and $0.32. Costs use the listed standard API rates.
Which has the larger context window, Claude Fable 5.2 or Muse Wonder?
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 evidence39 rows
Agentic
Terminal-Bench 4.0
Claude Fable 5.267.60%SourceMuse Wonder—Not directly comparable
Terminal-Bench-Science 0.1
Claude Fable 5.274.6%SourceMuse Wonder—Not directly comparable
AutomationBench
Claude Fable 5.251.4%SourceMuse Wonder—Not directly comparable
OSWorld 2.1 Offline
Claude Fable 5.289.3%SourceMuse Wonder—Not directly comparable
WANDR
Claude Fable 5.282.1%SourceMuse Wonder—Not directly comparable
Remote Labor Index
Claude Fable 5.241.3%SourceMuse Wonder—Not directly comparable
RoboDojo Sim
Claude Fable 5.264.9%SourceMuse Wonder—Not directly comparable
DRACO
Claude Fable 5.287.7%SourceMuse Wonder—Not directly comparable
JobBench
Claude Fable 5.2—Muse Wonder70.5%SourceNot directly comparable
Finance Agent v2
Claude Fable 5.2—Muse Wonder56.6%SourceNot directly comparable
MazeBench
Claude Fable 5.2—Muse Wonder0%SourceNot directly comparable
OSWorld 2.1
Claude Fable 5.2—Muse Wonder72.6%SourceNot directly comparable
CWE-bench
Claude Fable 5.2—Muse Wonder66.1%SourceNot directly comparable
Coding
SWE-bench Pro
Claude Fable 5.293%SourceMuse Wonder—Not directly comparable
SWE Multilingual
Claude Fable 5.296.6%SourceMuse Wonder—Not directly comparable
SWE Multimodal
Claude Fable 5.274.1%SourceMuse Wonder—Not directly comparable
DeepSWE
Claude Fable 5.274.3%SourceMuse Wonder78.8%SourceMuse Wonder leads this result
FrontierSWE v2
Claude Fable 5.269.9%SourceMuse Wonder—Not directly comparable
ProgramBench
Claude Fable 5.285.6%SourceMuse Wonder50.0%SourceClaude Fable 5.2 leads this result
FrontierCode 2.0
Shared sourceClaude Fable 5.249.1%Muse Wonder24.3%Claude Fable 5.2 leads this result
CursorBench 4.0
Claude Fable 5.260.0%SourceMuse Wonder—Not directly comparable
sweMarathon
Claude Fable 5.2—Muse Wonder53.1%SourceNot directly comparable
Bug Hunt Bench
Claude Fable 5.2—Muse Wonder31.7 fixesSourceNot directly comparable
Reasoning
ARC-AGI-3
Claude Fable 5.265.7%SourceMuse Wonder—Not directly comparable
ARC-AGI-3 Provider Adapter
Claude Fable 5.294.90%SourceMuse Wonder—Not directly comparable
STEM Professor Bench
Claude Fable 5.261.8%SourceMuse Wonder—Not directly comparable
STEMBench
Claude Fable 5.2—Muse Wonder2.68SourceNot directly comparable
Multimodal
Chartography (no tools)
Claude Fable 5.273.4%SourceMuse Wonder—Not directly comparable
Chartography (tools)
Claude Fable 5.291.6%SourceMuse Wonder—Not directly comparable
OfficeQA
Claude Fable 5.283.4%SourceMuse Wonder—Not directly comparable
OfficeQA Pro
Claude Fable 5.272.9%SourceMuse Wonder—Not directly comparable
BenchCAD 2.1
Claude Fable 5.275.4%SourceMuse Wonder—Not directly comparable
BenchCAD 2.1 (tools)
Claude Fable 5.283.5%SourceMuse Wonder—Not directly comparable
Knowledge
HLE
Claude Fable 5.274.2%SourceMuse Wonder—Not directly comparable
HLE w/o tools
Claude Fable 5.273.2%SourceMuse Wonder—Not directly comparable
PhysicianBench
Claude Fable 5.264.4%SourceMuse Wonder—Not directly comparable
HealthBench Professional
Claude Fable 5.2—Muse Wonder60.5%SourceNot directly comparable
Multilingual
39 public results · 3 shared
Watch Claude Fable 5.2 vs Muse Wonder
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