Agentic
Like-for-like- Claude Opus 4.6
- 50.1
- Supported · #58/152
- Claude Sonnet 5
- 65.8
- Supported · #11/152
- Basis
- BenchAlign lane · 9 vs 6 public rows
- Reading
- Claude Sonnet 5 leads
Claude Opus 4.6 vs Claude Sonnet 5
Updated September 8, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Claude Sonnet 5 has the higher public score estimate, 69.8 versus 69, 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.
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 Sonnet 5
Claude Sonnet 5 leads on the public coding lane, 64.1 to 56.7, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Claude Sonnet 5
Claude Sonnet 5 leads on the public agentic lane, 65.8 to 50.1, 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
Show secondary and unsupported calls
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. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback
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
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
25 Claude Opus 4.6 only
8 Shared
16 Claude Sonnet 5 only
- Shared results
- 8
- Claude Opus 4.6 only
- 25
- Claude Sonnet 5 only
- 16
- Like-for-like categories
- 2 / 8
2 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
Like-for-like- Claude Opus 4.6
- 56.7
- Supported · #37/151
- Claude Sonnet 5
- 64.1
- Supported · #13/151
- Basis
- BenchAlign lane · 8 vs 10 public rows
- Reading
- Claude Sonnet 5 leads · intervals overlap
Knowledge
Directional only- Claude Opus 4.6
- 61.2
- Estimated · #34/182
- Claude Sonnet 5
- 66.7
- Supported · #20/182
- Basis
- BenchAlign lane · 9 vs 6 public rows
- Reading
- Directional only
Multimodal
Directional only- Claude Opus 4.6
- 59.5
- #28/48
- Claude Sonnet 5
- 77.5
- #13/48
- Basis
- Provisional lane · 1 vs 1 weighted rows
- Reading
- Directional only
Reasoning
Not comparable- Claude Opus 4.6
- 67.1
- Unranked · 2 rankable rows
- Claude Sonnet 5
- 77.4
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Claude Opus 4.6
- 58.6
- Unranked · 3 rankable rows
- Claude Sonnet 5
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Claude Opus 4.6
- Not ranked
- Claude Sonnet 5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Claude Opus 4.6
- 52.6
- #77/121
- Claude Sonnet 5
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | Claude Opus 4.6 | Claude Sonnet 5 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 50.1Supported · #58/152 | 65.8Supported · #11/152 | Like-for-likeBenchAlign lane · 9 vs 6 public rows | Claude Sonnet 5 leads |
| Coding | 56.7Supported · #37/151 | 64.1Supported · #13/151 | Like-for-likeBenchAlign lane · 8 vs 10 public rows | Claude Sonnet 5 leads · intervals overlap |
| Knowledge | 61.2Estimated · #34/182 | 66.7Supported · #20/182 | Directional onlyBenchAlign lane · 9 vs 6 public rows | Directional only |
| Multimodal | 59.5#28/48 | 77.5#13/48 | Directional onlyProvisional lane · 1 vs 1 weighted rows | Directional only |
| Reasoning | 67.1Unranked · 2 rankable rows | 77.4Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 58.6Unranked · 3 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 52.6#77/121 | 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.
Terminal-Bench 2.0
Agentic
Claude Opus 4.6: 65.4%Claude Sonnet 5: 80.4%Normalized gap 15.0Claude Opus 4.6 source Claude Sonnet 5 sourceSWE-bench Pro
Coding
Claude Opus 4.6: 53.4%Claude Sonnet 5: 63.2%Normalized gap 9.8Claude Opus 4.6 source Claude Sonnet 5 sourceOSWorld-Verified
Agentic
Claude Opus 4.6: 72.7%Claude Sonnet 5: 81.2%Normalized gap 8.5Claude Opus 4.6 source Claude Sonnet 5 sourceHLE
Knowledge
Claude Opus 4.6: 53%Claude Sonnet 5: 57.4%Normalized gap 4.4Claude Opus 4.6 source Claude Sonnet 5 sourceSWE-bench Verified
Coding
Claude Opus 4.6: 80.8%Claude Sonnet 5: 85.2%Normalized gap 4.4Claude Opus 4.6 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 4.6
- $0.0175
- 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 4.6
- $0.325
- 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 4.6
- $1.35
- Fits in one request
- Cached input priced at the published list-input rate
- Claude Sonnet 5
- $0.18
- Fits in one request
Claude Sonnet 5 has the lower modeled cost
Claude Opus 4.6 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 Opus 4.6Claude Sonnet 5
Context window
Maximum documented context; output-token limits may be lower.
Claude Opus 4.6
1M
Claude Sonnet 5
API model ID
Claude Opus 4.6
Not sourced
Claude 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 4.6
Not published
Claude Sonnet 5
$0.2 per 1M cached input tokens
Claude API pricingDocumented inputs
Claude Opus 4.6
Not sourced
Claude Sonnet 5
text, image
Anthropic model overviewDocumented outputs
Claude Opus 4.6
Not sourced
Claude Sonnet 5
Provider availability
Claude Opus 4.6
Not sourced
Claude Sonnet 5
Generally Available · Claude API
Anthropic model overviewReasoning profile
Claude Opus 4.6
Non-Reasoning
Claude Sonnet 5
Reasoning
Weight access
Claude Opus 4.6
Proprietary
Claude Sonnet 5
Proprietary
License
Claude Opus 4.6
Proprietary
Claude Sonnet 5
Proprietary
Release date
Claude Opus 4.6
2026-02-01
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 Sonnet 5 has the higher public score estimate, 69.8 versus 69, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.325 vs $0.13. Cache-heavy agent loop: $1.35 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 evidence49 rows
Agentic
Terminal-Bench 2.0
Claude Opus 4.665.4%SourceClaude Sonnet 580.4%SourceClaude Sonnet 5 leads this result
BrowseComp
Claude Opus 4.683.7%SourceClaude Sonnet 584.7%SourceClaude Sonnet 5 leads this result
OSWorld-Verified
Claude Opus 4.672.7%SourceClaude Sonnet 581.2%SourceClaude Sonnet 5 leads this result
Claw-Eval
Claude Opus 4.670.4%SourceClaude Sonnet 5—Not directly comparable
DeepSearchQA
Claude Opus 4.673.7%SourceClaude Sonnet 5—Not directly comparable
CyberGym
Claude Opus 4.666.6%SourceClaude Sonnet 5—Not directly comparable
Gert Labs
Claude Opus 4.661.85%SourceClaude Sonnet 5—Not directly comparable
ResearchClawBench
Claude Opus 4.619.9%SourceClaude Sonnet 5—Not directly comparable
JobBench
Claude Opus 4.636.7%SourceClaude Sonnet 5—Not directly comparable
Terminal-Bench 3.0
Claude Opus 4.6—Claude Sonnet 514.6%SourceNot directly comparable
HLE w/ tools
Claude Opus 4.6—Claude Sonnet 557.4%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
Claude Opus 4.6—Claude Sonnet 574.5%SourceNot directly comparable
Coding
SWE-bench Verified
Claude Opus 4.680.8%SourceClaude Sonnet 585.2%SourceClaude Sonnet 5 leads this result
SWE-bench Verified*
Claude Opus 4.675.6%SourceClaude Sonnet 5—Not directly comparable
LiveCodeBench Pro
Claude Opus 4.670.7%SourceClaude Sonnet 5—Not directly comparable
SWE-bench Pro
Claude Opus 4.653.4%SourceClaude Sonnet 563.2%SourceClaude Sonnet 5 leads this result
SWE-Rebench
Claude Opus 4.665.3%SourceClaude Sonnet 5—Not directly comparable
React Native Evals
Claude Opus 4.684.1%SourceClaude Sonnet 5—Not directly comparable
Vibe Code Bench
Claude Opus 4.657.57%SourceClaude Sonnet 5—Not directly comparable
FrontierCode 1.1 Main
Shared sourceClaude Opus 4.626.9%Claude Sonnet 542.7%Claude Sonnet 5 leads this result
SWE Multilingual
Claude Opus 4.6—Claude Sonnet 578.3%SourceNot directly comparable
SWE Multimodal
Claude Opus 4.6—Claude Sonnet 528.1%SourceNot directly comparable
Terminal-Bench 2.0
Claude Opus 4.6—Claude Sonnet 580.4%SourceNot directly comparable
cursorBench32
Claude Opus 4.6—Claude Sonnet 561.5%SourceNot directly comparable
VulcanBench CII v1
Claude Opus 4.6—Claude Sonnet 589.2%SourceNot directly comparable
LiveCodeBench (Vals)
Claude Opus 4.6—Claude Sonnet 582.4%SourceNot directly comparable
SWE-bench (Vals)
Claude Opus 4.6—Claude Sonnet 579.6%SourceNot directly comparable
Knowledge
GPQA
Claude Opus 4.691.3%SourceClaude Sonnet 5—Not directly comparable
GPQA-D
Claude Opus 4.689.2%SourceClaude Sonnet 5—Not directly comparable
SuperGPQA
Claude Opus 4.695%SourceClaude Sonnet 5—Not directly comparable
MMLU-Pro
Claude Opus 4.682%SourceClaude Sonnet 5—Not directly comparable
MMLU-Pro (Arcee)
Claude Opus 4.689.1%SourceClaude Sonnet 5—Not directly comparable
HLE
Claude Opus 4.653%SourceClaude Sonnet 557.4%SourceClaude Sonnet 5 leads this result
HLE w/o tools
Claude Opus 4.640%SourceClaude Sonnet 543.2%SourceClaude Sonnet 5 leads this result
HealthBench Hard
Claude Opus 4.614.8%SourceClaude Sonnet 5—Not directly comparable
MedXpertQA (Text)
Claude Opus 4.652.1%SourceClaude Sonnet 5—Not directly comparable
HLE-Verified
Claude Opus 4.6—Claude Sonnet 531.0%SourceNot directly comparable
LABBench2
Claude Opus 4.6—Claude Sonnet 580.1%SourceNot directly comparable
GPQA Diamond (Vals)
Claude Opus 4.6—Claude Sonnet 588.9%SourceNot directly comparable
MMLU-Pro (Vals)
Claude Opus 4.6—Claude Sonnet 587.5%SourceNot directly comparable
Math
Multimodal
MMMU-Pro
Claude Opus 4.677.3%SourceClaude Sonnet 5—Not directly comparable
ERQA
Claude Opus 4.651.6%SourceClaude Sonnet 5—Not directly comparable
ScreenSpot Pro
Claude Opus 4.683.1%SourceClaude Sonnet 5—Not directly comparable
MedXpertQA (MM)
Claude Opus 4.664.8%SourceClaude Sonnet 5—Not directly comparable
CharXiv
Claude Opus 4.6—Claude Sonnet 588.3%SourceNot directly comparable
CharXiv w/o tools
Claude Opus 4.6—Claude Sonnet 577%SourceNot directly comparable
Frequently asked questions
Which is better, Claude Opus 4.6 or Claude Sonnet 5?
Claude Sonnet 5 has the higher public score estimate, 69.8 versus 69, 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 4.6 or Claude Sonnet 5?
Claude Sonnet 5 leads the public coding lane, 64.1 to 56.7, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, Claude Opus 4.6 or Claude Sonnet 5?
Claude Sonnet 5 leads the public agentic tasks lane, 65.8 to 50.1, with Supported evidence for both models and non-overlapping 90% intervals.
Which costs less, Claude Opus 4.6 or Claude Sonnet 5?
For the stated presets, chat costs $0.0175 on Claude Opus 4.6 and $0.007 on Claude Sonnet 5; repository review costs $0.325 and $0.13; the cache-heavy agent loop costs $1.35 and $0.18. Claude Opus 4.6 has no published cached-input rate, so cached tokens use its listed input rate.
Which has the larger context window, Claude Opus 4.6 or Claude Sonnet 5?
Both models list the same context window, 1M.
Related comparisons
Last updated September 8, 2026
Watch Claude Opus 4.6 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.