Coding
Like-for-like- Claude 4 Sonnet
- 38.0
- Supported · #149/183
- Claude Fable 5
- 76.9
- Supported · #2/183
- Basis
- BenchAlign lane · 1 vs 10 public rows
- Reading
- Claude Fable 5 leads
Claude 4 Sonnet vs Claude Fable 5
Updated September 4, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Fable 5 has the higher public score, 80.9 versus 41.76, and the 90% score intervals do not overlap.
1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Share or export
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.
Coding work
Code generation, repair, and software-engineering tasks
Claude Fable 5
Claude Fable 5 leads on the public coding lane, 76.9 to 38, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Long documents
Prompts that approach the documented context limit
Claude Fable 5
Claude Fable 5 has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
Claude 4 Sonnet
Claude 4 Sonnet 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 4 Sonnet
Claude 4 Sonnet has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Claude 4 Sonnet is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude 4 Sonnet does not fit this workload in one request. Claude 4 Sonnet has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
2 Claude 4 Sonnet only
1 Shared
17 Claude Fable 5 only
- Shared results
- 1
- Claude 4 Sonnet only
- 2
- Claude Fable 5 only
- 17
- Like-for-like categories
- 1 / 8
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, 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.
Agentic
Directional only- Claude 4 Sonnet
- 42.3
- Estimated · #115/151
- Claude Fable 5
- 74.8
- Supported · #3/151
- Basis
- BenchAlign lane · 2 vs 4 public rows
- Reading
- Directional only
Knowledge
Directional only- Claude 4 Sonnet
- 41.0
- Estimated · #134/181
- Claude Fable 5
- 83.5
- Supported · #2/181
- Basis
- BenchAlign lane · 0 vs 2 public rows
- Reading
- Directional only
Instruction following
Directional only- Claude 4 Sonnet
- 53.4
- #75/120
- Claude Fable 5
- 78.3
- #54/120
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- Claude 4 Sonnet
- 53.9
- Unranked · 2 rankable rows
- Claude Fable 5
- 76.2
- #11/22
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude 4 Sonnet
- Not ranked
- Claude Fable 5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude 4 Sonnet
- Not ranked
- Claude Fable 5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Claude 4 Sonnet
- 51.9
- Unranked · 1 rankable row
- Claude Fable 5
- 62.5
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
| Category | Claude 4 Sonnet | Claude Fable 5 | Basis | Reading |
|---|---|---|---|---|
| Coding | 38.0Supported · #149/183 | 76.9Supported · #2/183 | Like-for-likeBenchAlign lane · 1 vs 10 public rows | Claude Fable 5 leads |
| Agentic | 42.3Estimated · #115/151 | 74.8Supported · #3/151 | Directional onlyBenchAlign lane · 2 vs 4 public rows | Directional only |
| Knowledge | 41.0Estimated · #134/181 | 83.5Supported · #2/181 | Directional onlyBenchAlign lane · 0 vs 2 public rows | Directional only |
| Instruction following | 53.4#75/120 | 78.3#54/120 | Directional onlyProvisional lane · 0 vs 0 weighted rows | Directional only |
| Reasoning | 53.9Unranked · 2 rankable rows | 76.2#11/22 | 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 |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 51.9Unranked · 1 rankable row | 62.5Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
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.
SWE-bench Verified
Coding
Claude 4 Sonnet: 72.7%Claude Fable 5: 95%Normalized gap 22.3Claude 4 Sonnet source Claude Fable 5 source
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 4 Sonnet
- $0.0105
- Fits in one request
- Claude Fable 5
- $0.035
- Fits in one request
Claude 4 Sonnet has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude 4 Sonnet
- $0.195
- Fits in one request
- Claude Fable 5
- $0.65
- Fits in one request
Claude 4 Sonnet 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 4 Sonnet
- $0.81
- Does not fit in one request
- Cached input priced at the published list-input rate
- Claude Fable 5
- $0.9
- Fits in one request
Claude 4 Sonnet does not fit this workload in one request. Claude 4 Sonnet has no published cached-input rate, so cached tokens use its listed input rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude 4 SonnetClaude Fable 5
Context window
Maximum documented context; output-token limits may be lower.
Claude 4 Sonnet
200K
Claude Fable 5
API model ID
Claude 4 Sonnet
Not sourced
Claude Fable 5
claude-fable-5
Anthropic model overviewCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude 4 Sonnet
Not published
Claude Fable 5
$1 per 1M cached input tokens
Claude API pricingDocumented inputs
Claude 4 Sonnet
Not sourced
Claude Fable 5
text, image
Anthropic model overviewDocumented outputs
Claude 4 Sonnet
Not sourced
Claude Fable 5
Provider availability
Claude 4 Sonnet
Not sourced
Claude Fable 5
Generally Available · Claude API
Anthropic model overviewReasoning profile
Claude 4 Sonnet
Non-Reasoning
Claude Fable 5
Reasoning
Weight access
Claude 4 Sonnet
Proprietary
Claude Fable 5
Proprietary
License
Claude 4 Sonnet
Proprietary
Claude Fable 5
Proprietary
Release date
Claude 4 Sonnet
2025-05-01
Claude Fable 5
2026-06-09
If you already use one of these models
- Deployment change
- Both entries list Anthropic as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Claude Fable 5 has the higher public score, 80.9 versus 41.76, and the 90% score intervals do not overlap.
- Workload cost
- Repository review: $0.195 vs $0.65. Cache-heavy agent loop: $0.81 vs $0.9.
- Context tradeoff
- Claude Fable 5 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence20 rows
Agentic
Gert Labs
Claude 4 Sonnet39.66%SourceClaude Fable 5—Not directly comparable
JobBench
Claude 4 Sonnet18.4%SourceClaude Fable 5—Not directly comparable
Terminal-Bench 3.0
Claude 4 Sonnet—Claude Fable 534.0%SourceNot directly comparable
Terminal-Bench 2.0
Claude 4 Sonnet—Claude Fable 584.3%SourceNot directly comparable
OSWorld-Verified
Claude 4 Sonnet—Claude Fable 585%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
Claude 4 Sonnet—Claude Fable 580.5%SourceNot directly comparable
Coding
SWE-bench Verified
Claude 4 Sonnet72.7%SourceClaude Fable 595%SourceClaude Fable 5 leads this result
SWE-bench Pro
Claude 4 Sonnet—Claude Fable 580%SourceNot directly comparable
FrontierSWE v2
Claude 4 Sonnet—Claude Fable 548.0%SourceNot directly comparable
FrontierCode 1.1 Main
Claude 4 Sonnet—Claude Fable 553.5%SourceNot directly comparable
Terminal-Bench 2.0
Claude 4 Sonnet—Claude Fable 584.3%SourceNot directly comparable
cursorBench31
Claude 4 Sonnet—Claude Fable 570.6%SourceNot directly comparable
cursorBench32
Claude 4 Sonnet—Claude Fable 570.5%SourceNot directly comparable
VulcanBench v3
Claude 4 Sonnet—Claude Fable 589.5%SourceNot directly comparable
LiveCodeBench (Vals)
Claude 4 Sonnet—Claude Fable 589.8%SourceNot directly comparable
SWE-bench (Vals)
Claude 4 Sonnet—Claude Fable 595.0%SourceNot directly comparable
Knowledge
Multimodal
Frequently asked questions
Which is better, Claude 4 Sonnet or Claude Fable 5?
Claude Fable 5 has the higher public score, 80.9 versus 41.76, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Claude 4 Sonnet or Claude Fable 5?
Claude Fable 5 leads the public coding lane, 76.9 to 38, with Supported evidence for both models and non-overlapping 90% intervals.
Which is better for agentic tasks, Claude 4 Sonnet or Claude Fable 5?
Claude Fable 5 scores higher for agentic tasks on the public lane, 74.8 to 42.3. Claude 4 Sonnet 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 4 Sonnet or Claude Fable 5?
For the stated presets, chat costs $0.0105 on Claude 4 Sonnet and $0.035 on Claude Fable 5; repository review costs $0.195 and $0.65; the cache-heavy agent loop costs $0.81 and $0.9. Claude 4 Sonnet does not fit this workload in one request. Claude 4 Sonnet has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude 4 Sonnet or Claude Fable 5?
Claude Fable 5 has the larger documented context window: 1M, compared with 200K.
Related comparisons
Last updated September 4, 2026
Watch Claude 4 Sonnet vs Claude Fable 5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.