Agentic
Like-for-like- Claude Opus 5.5
- 82.7
- Supported · #1/156
- Claude Sonnet 5
- 66.2
- Supported · #13/156
- Basis
- BenchAlign lane · 11 vs 7 public rows
- Reading
- Claude Opus 5.5 leads
Claude Opus 5.5 vs Claude Sonnet 5
Decision reading
Claude Opus 5.5 has the higher public score estimate, 81.03 versus 69.52, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
8 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Updated September 22, 2026. Rank says Claude Opus 5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
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.
Agentic work
Tool use, computer use, and multi-step task completion
Claude Opus 5.5
Claude Opus 5.5 leads on the public agentic lane, 82.7 to 66.2, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Chat turn cost
1K fresh input + 500 output tokens
Claude Sonnet 5
Claude Sonnet 5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Claude Sonnet 5
Claude Sonnet 5 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 Sonnet 5
Claude Sonnet 5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Claude Opus 5.5 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Confidence: limited
Long 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.
76.0Claude Opus 5.563.9Claude Sonnet 5
Directional only · BenchAlign
Claude Opus 5.5 scores higher, but at least one score rests on Estimated evidence or a different benchmark set. Directional only, no winner.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
40 Claude Opus 5.5 only
8 Shared
18 Claude Sonnet 5 only
- Shared results
- 8
- Claude Opus 5.5 only
- 40
- Claude Sonnet 5 only
- 18
- 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.
Coding
Directional only- Claude Opus 5.5
- 76.0
- Estimated · #4/159
- Claude Sonnet 5
- 63.9
- Supported · #16/159
- Basis
- BenchAlign lane · 9 vs 11 public rows
- Reading
- Directional only
Multimodal
Directional only- Claude Opus 5.5
- 88.8
- #3/50
- Claude Sonnet 5
- 77.4
- #15/50
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Directional only
Knowledge
Directional only- Claude Opus 5.5
- 81.5
- Estimated · #3/187
- Claude Sonnet 5
- 66.2
- Supported · #21/187
- Basis
- BenchAlign lane · 17 vs 6 public rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Opus 5.5
- 78.5
- #4/19
- Claude Sonnet 5
- 77.4
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 5.5
- Not ranked
- Claude Sonnet 5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 5.5
- Not ranked
- Claude Sonnet 5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 5.5
- Not ranked
- Claude Sonnet 5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Opus 5.5 | Claude Sonnet 5 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 82.7Supported · #1/156 | 66.2Supported · #13/156 | Like-for-likeBenchAlign lane · 11 vs 7 public rows | Claude Opus 5.5 leads |
| Coding | 76.0Estimated · #4/159 | 63.9Supported · #16/159 | Directional onlyBenchAlign lane · 9 vs 11 public rows | Directional only |
| Multimodal | 88.8#3/50 | 77.4#15/50 | Directional onlyProvisional lane · 1 vs 1 weighted rows | Directional only |
| Knowledge | 81.5Estimated · #3/187 | 66.2Supported · #21/187 | Directional onlyBenchAlign lane · 17 vs 6 public rows | Directional only |
| Reasoning | 78.5#4/19 | 77.4Unranked · 2 rankable rows | 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 |
| 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, 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 Pro
Coding
Claude Opus 5.5: 89.9%Claude Sonnet 5: 63.2%Normalized gap 26.7Claude Opus 5.5 source Claude Sonnet 5 sourceHLE w/o tools
Knowledge
Claude Opus 5.5: 64.4%Claude Sonnet 5: 43.2%Normalized gap 21.2Claude Opus 5.5 source Claude Sonnet 5 sourceSWE Multilingual
Coding
Claude Opus 5.5: 93.9%Claude Sonnet 5: 78.3%Normalized gap 15.6Claude Opus 5.5 source Claude Sonnet 5 sourceHLE
Knowledge
Claude Opus 5.5: 67.7%Claude Sonnet 5: 57.4%Normalized gap 10.3Claude Opus 5.5 source Claude Sonnet 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 Opus 5.5
- $0.014
- Fits in one request
- Claude Sonnet 5
- $0.007
- Fits in one request
Claude Sonnet 5 has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Claude Opus 5.5
- $0.26
- Fits in one request
- Claude Sonnet 5
- $0.13
- Fits in one request
Claude Sonnet 5 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 Opus 5.5
- $0.32
- Fits in one request
- Claude Sonnet 5
- $0.18
- Fits in one request
Claude Sonnet 5 has the lower modeled cost
Costs use the listed standard API rates.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationClaude Opus 5.5Claude Sonnet 5
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 5.5
Claude Sonnet 5
API model ID
Claude Opus 5.5
claude-opus-5-5
Anthropic Claude Opus 5.5 model documentationClaude Sonnet 5
claude-sonnet-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 Opus 5.5
$0.2 per 1M cached input tokens
Claude Opus 5.5 model documentationClaude Sonnet 5
$0.2 per 1M cached input tokens
Claude API pricingDocumented inputs
Claude Opus 5.5
Claude Sonnet 5
text, image
Anthropic model overviewDocumented outputs
Claude Opus 5.5
Claude Sonnet 5
Provider availability
Claude Opus 5.5
Generally Available · Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry, Claude Platform on AWS
Anthropic Claude Opus 5.5 model documentationClaude Sonnet 5
Generally Available · Claude API
Anthropic model overviewReasoning profile
Claude Opus 5.5
Reasoning
Claude Sonnet 5
Reasoning
Weight access
Claude Opus 5.5
Proprietary
Claude Sonnet 5
Proprietary
License
Claude Opus 5.5
Proprietary
Claude Sonnet 5
Proprietary
Release date
Claude Opus 5.5
2026-09-22
Claude Sonnet 5
2026-06-30
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 Opus 5.5 has the higher public score estimate, 81.03 versus 69.52, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.26 vs $0.13. Cache-heavy agent loop: $0.32 vs $0.18.
- Context tradeoff
- Both models list 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 evidence66 rows
Agentic
Terminal-Bench 4.0
Claude Opus 5.566.40%SourceClaude Sonnet 5—Not directly comparable
Terminal-Bench-Science 0.1
Claude Opus 5.558.7%SourceClaude Sonnet 5—Not directly comparable
AutomationBench
Claude Opus 5.540.0%SourceClaude Sonnet 5—Not directly comparable
HLE w/ tools
Claude Opus 5.567.7%SourceClaude Sonnet 557.4%SourceClaude Opus 5.5 leads this result
OSWorld 2.0
Claude Opus 5.548.7%SourceClaude Sonnet 5—Not directly comparable
LAB all-pass (Harvey held-out)
Claude Opus 5.58.3%SourceClaude Sonnet 5—Not directly comparable
LAB criterion-pass (Harvey held-out)
Claude Opus 5.591.2%SourceClaude Sonnet 5—Not directly comparable
Toolathlon-Verified
Claude Opus 5.577.8%SourceClaude Sonnet 5—Not directly comparable
Toolathlon Verified Pass@3
Claude Opus 5.582.4%SourceClaude Sonnet 5—Not directly comparable
Toolathlon Verified Pass³
Claude Opus 5.572.2%SourceClaude Sonnet 5—Not directly comparable
Toolathlon Verified avg. turns
Claude Opus 5.526.9 turnsSourceClaude Sonnet 5—Not directly comparable
Terminal-Bench 3.0
Claude Opus 5.5—Claude Sonnet 514.6%SourceNot directly comparable
Terminal-Bench 2.0
Claude Opus 5.5—Claude Sonnet 580.4%SourceNot directly comparable
BrowseComp
Claude Opus 5.5—Claude Sonnet 584.7%SourceNot directly comparable
OSWorld-Verified
Claude Opus 5.5—Claude Sonnet 581.2%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
Claude Opus 5.5—Claude Sonnet 574.5%SourceNot directly comparable
ApprenticeBench
Claude Opus 5.5—Claude Sonnet 516%SourceNot directly comparable
Coding
FrontierCode 1.1 Main
Claude Opus 5.554.4%SourceClaude Sonnet 542.7%SourceClaude Opus 5.5 leads this result
cursorBench40
Shared sourceClaude Opus 5.557.8%Claude Sonnet 534.1%Claude Opus 5.5 leads this result
SWE-bench Pro
Claude Opus 5.589.9%SourceClaude Sonnet 563.2%SourceClaude Opus 5.5 leads this result
SWE Multilingual
Claude Opus 5.593.9%SourceClaude Sonnet 578.3%SourceClaude Opus 5.5 leads this result
SWE Multimodal
Claude Opus 5.561.4%SourceClaude Sonnet 528.1%SourceClaude Opus 5.5 leads this result
DeepSWE
Claude Opus 5.574.2%SourceClaude Sonnet 5—Not directly comparable
FrontierCode 1.1 Extended
Claude Opus 5.563.6%SourceClaude Sonnet 5—Not directly comparable
FrontierSWE v2
Claude Opus 5.562.3%SourceClaude Sonnet 5—Not directly comparable
ProgramBench
Claude Opus 5.591.2%SourceClaude Sonnet 5—Not directly comparable
SWE-bench Verified
Claude Opus 5.5—Claude Sonnet 585.2%SourceNot directly comparable
Terminal-Bench 2.0
Claude Opus 5.5—Claude Sonnet 580.4%SourceNot directly comparable
cursorBench32
Claude Opus 5.5—Claude Sonnet 561.5%SourceNot directly comparable
VulcanBench CII v1
Claude Opus 5.5—Claude Sonnet 589.2%SourceNot directly comparable
LiveCodeBench (Vals)
Claude Opus 5.5—Claude Sonnet 582.4%SourceNot directly comparable
SWE-bench (Vals)
Claude Opus 5.5—Claude Sonnet 579.6%SourceNot directly comparable
Multimodal
Chartography (tools)
Claude Opus 5.589.0%SourceClaude Sonnet 5—Not directly comparable
Chartography (no tools)
Claude Opus 5.564.4%SourceClaude Sonnet 5—Not directly comparable
BenchCAD Vision2Code (no tools)
Claude Opus 5.50.730SourceClaude Sonnet 5—Not directly comparable
BenchCAD Vision2Code (tools)
Claude Opus 5.50.962SourceClaude Sonnet 5—Not directly comparable
Biomedical image analysis
Claude Opus 5.571.4%SourceClaude Sonnet 5—Not directly comparable
OfficeQA
Claude Opus 5.578.9%SourceClaude Sonnet 5—Not directly comparable
OfficeQA Pro
Claude Opus 5.567.7%SourceClaude Sonnet 5—Not directly comparable
CharXiv
Claude Opus 5.5—Claude Sonnet 588.3%SourceNot directly comparable
CharXiv w/o tools
Claude Opus 5.5—Claude Sonnet 577%SourceNot directly comparable
Knowledge
HLE
Claude Opus 5.567.7%SourceClaude Sonnet 557.4%SourceClaude Opus 5.5 leads this result
HLE w/o tools
Claude Opus 5.564.4%SourceClaude Sonnet 543.2%SourceClaude Opus 5.5 leads this result
HealthBench (raw)
Claude Opus 5.568.1%SourceClaude Sonnet 5—Not directly comparable
HealthBench (length-adjusted)
Claude Opus 5.560.6%SourceClaude Sonnet 5—Not directly comparable
HealthBench Professional
Claude Opus 5.565.6%SourceClaude Sonnet 5—Not directly comparable
HealthBench Professional (raw)
Claude Opus 5.577.1%SourceClaude Sonnet 5—Not directly comparable
BioMysteryBench (human-solvable)
Claude Opus 5.589.3%SourceClaude Sonnet 5—Not directly comparable
BioMysteryBench (human-difficult)
Claude Opus 5.550.0%SourceClaude Sonnet 5—Not directly comparable
SpatialBench Verified
Claude Opus 5.572.0%SourceClaude Sonnet 5—Not directly comparable
SingleCellBench
Claude Opus 5.561.2%SourceClaude Sonnet 5—Not directly comparable
Morphology-to-molecule matching
Claude Opus 5.534.0%SourceClaude Sonnet 5—Not directly comparable
Medicinal chemistry
Claude Opus 5.563.5%SourceClaude Sonnet 5—Not directly comparable
Protein Design
Claude Opus 5.560.2%SourceClaude Sonnet 5—Not directly comparable
Protein Design library ranking
Claude Opus 5.556.0%SourceClaude Sonnet 5—Not directly comparable
De novo protein-binder design
Claude Opus 5.582.6%SourceClaude Sonnet 5—Not directly comparable
Protocols (troubleshooting)
Claude Opus 5.573.7%SourceClaude Sonnet 5—Not directly comparable
Protocols (understanding)
Claude Opus 5.569.0%SourceClaude Sonnet 5—Not directly comparable
HLE-Verified
Claude Opus 5.5—Claude Sonnet 531.0%SourceNot directly comparable
LABBench2
Claude Opus 5.5—Claude Sonnet 580.1%SourceNot directly comparable
GPQA Diamond (Vals)
Claude Opus 5.5—Claude Sonnet 588.9%SourceNot directly comparable
MMLU-Pro (Vals)
Claude Opus 5.5—Claude Sonnet 587.5%SourceNot directly comparable
Multilingual
Math
Questions
Which is better, Claude Opus 5.5 or Claude Sonnet 5?
Claude Opus 5.5 has the higher public score estimate, 81.03 versus 69.52, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Claude Opus 5.5 or Claude Sonnet 5?
Claude Opus 5.5 scores higher for coding on the public lane, 76 to 63.9. Claude Opus 5.5 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 Opus 5.5 or Claude Sonnet 5?
Claude Opus 5.5 leads the public agentic tasks lane, 82.7 to 66.2, with Supported evidence for both models and non-overlapping 90% intervals.
Which costs less, Claude Opus 5.5 or Claude Sonnet 5?
For the stated presets, chat costs $0.014 on Claude Opus 5.5 and $0.007 on Claude Sonnet 5; repository review costs $0.26 and $0.13; the cache-heavy agent loop costs $0.32 and $0.18. Costs use the listed standard API rates.
Which has the larger context window, Claude Opus 5.5 or Claude Sonnet 5?
Both models list the same context window, 1M.
Related comparisons
Last updated September 22, 2026
Watch Claude Opus 5.5 vs Claude Sonnet 5
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.