Skip to main content
BenchLM

Claude Opus 5.5 vs Claude Sonnet 5.5

Updated September 28, 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.

Share or export
Share on XLinkedInSocial cardCSVJSON

Decision reading

Claude Opus 5.5 has the higher public score estimate, 87.07 versus 80.49, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 45 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Anthropic logo
Claude Opus 5.5

Anthropic

87.07/100

Estimated · Public rank #2

90% interval 75.5–98.6

Model B
Anthropic logo
Claude Sonnet 5.5

Anthropic

80.49/100

Estimated · Public rank #5

90% interval 69.0–92.0

Shared results
45
Claude Opus 5.5 only
4
Claude Sonnet 5.5 only
2
Like-for-like categories
2 / 8
Estimated: Claude Opus 5.5 and Claude Sonnet 5.5How 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.

  • 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, 87.8 to 66.1, with Supported evidence for both models and non-overlapping 90% intervals.

    Confidence: stronger

  • Chat turn cost

    1K fresh input + 500 output tokens

    Claude Sonnet 5.5

    Claude Sonnet 5.5 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 5.5

    Claude Sonnet 5.5 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 5.5

    Claude Sonnet 5.5 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 Sonnet 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.

83.0Claude Opus 5.579.6Claude Sonnet 5.5

Directional only · BenchAlign v5.7

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.

Open the coding leaderboardShortlist models for this job
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.

2 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.

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 v5.7 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

Like-for-like
Claude Opus 5.5
87.8
Supported · #1/111
Claude Sonnet 5.5
66.1
Supported · #10/111
Basis
BenchAlign v5.7 lane · 11 vs 11 public rows
Reading
Claude Opus 5.5 leads

Knowledge

Like-for-like
Claude Opus 5.5
89.1
Supported · #1/160
Claude Sonnet 5.5
80.9
Supported · #6/160
Basis
BenchAlign v5.7 lane · 16 vs 16 public rows
Reading
Claude Opus 5.5 leads · intervals overlap

Coding

Directional only
Claude Opus 5.5
83.0
Supported · #1/136
Claude Sonnet 5.5
79.6
Estimated · #3/136
Basis
BenchAlign v5.7 lane · 9 vs 9 public rows
Reading
Directional only

Reasoning

Directional only
Claude Opus 5.5
82.4
#2/27
Claude Sonnet 5.5
79.2
#7/27
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Directional only

Multimodal

Not comparable
Claude Opus 5.5
88.8
#3/50
Claude Sonnet 5.5
83.3
Unranked · 7 rankable rows
Basis
Provisional lane · 1 vs 1 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Claude Opus 5.5
Not ranked
Claude Sonnet 5.5
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 5.5
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Claude Opus 5.5
Not ranked
Claude Sonnet 5.5
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) 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 Opus 5.5
$0.014
Fits in one request
Claude Sonnet 5.5
$0.007
Fits in one request

Claude Sonnet 5.5 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 5.5
$0.13
Fits in one request

Claude Sonnet 5.5 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 5.5
$0.18
Fits in one request

Claude Sonnet 5.5 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.

Cached-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 documentation

Claude Sonnet 5.5

$0.2 per 1M cached input tokens

Claude API pricing

Reasoning profile

Claude Opus 5.5

Reasoning

Claude Sonnet 5.5

Reasoning

Weight access

Claude Opus 5.5

Proprietary

Claude Sonnet 5.5

Proprietary

License

Claude Opus 5.5

Proprietary

Claude Sonnet 5.5

Proprietary

Release date

Claude Opus 5.5

2026-09-22

Claude Sonnet 5.5

2026-09-28

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, 87.07 versus 80.49, 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.

Questions

Which is better, Claude Opus 5.5 or Claude Sonnet 5.5?

Claude Opus 5.5 has the higher public score estimate, 87.07 versus 80.49, 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 5.5?

Claude Opus 5.5 scores higher for coding on the public lane, 83 to 79.6. Claude Sonnet 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 5.5?

Claude Opus 5.5 leads the public agentic tasks lane, 87.8 to 66.1, with Supported evidence for both models and non-overlapping 90% intervals.

Which costs less, Claude Opus 5.5 or Claude Sonnet 5.5?

For the stated presets, chat costs $0.014 on Claude Opus 5.5 and $0.007 on Claude Sonnet 5.5; 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 5.5?

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 evidence51 rows

Agentic

  • Terminal-Bench 4.0

    Claude Opus 5.566.40%
    Source
    Claude Sonnet 5.570.60%
    Source

    Claude Sonnet 5.5 leads this result

  • Terminal-Bench-Science 0.1

    Claude Opus 5.558.7%
    Source
    Claude Sonnet 5.559.9%
    Source

    Claude Sonnet 5.5 leads this result

  • AutomationBench

    Claude Opus 5.540.0%
    Source
    Claude Sonnet 5.5—

    Not directly comparable

  • HLE w/ tools

    Claude Opus 5.567.7%
    Source
    Claude Sonnet 5.564.5%
    Source

    Claude Opus 5.5 leads this result

  • OSWorld 2.0

    Claude Opus 5.548.7%
    Source
    Claude Sonnet 5.5—

    Not directly comparable

  • LAB all-pass (Harvey held-out)

    Claude Opus 5.58.3%
    Source
    Claude Sonnet 5.510.0%
    Source

    Claude Sonnet 5.5 leads this result

  • LAB criterion-pass (Harvey held-out)

    Claude Opus 5.591.2%
    Source
    Claude Sonnet 5.593.1%
    Source

    Claude Sonnet 5.5 leads this result

  • Toolathlon-Verified

    Claude Opus 5.577.8%
    Source
    Claude Sonnet 5.577.8%
    Source

    Tie

  • Toolathlon Verified Pass@3

    Claude Opus 5.582.4%
    Source
    Claude Sonnet 5.585.2%
    Source

    Claude Sonnet 5.5 leads this result

  • Toolathlon Verified Pass³

    Claude Opus 5.572.2%
    Source
    Claude Sonnet 5.568.5%
    Source

    Claude Opus 5.5 leads this result

  • Toolathlon Verified avg. turns

    Claude Opus 5.526.9 turns
    Source
    Claude Sonnet 5.531.6 turns
    Source

    Claude Sonnet 5.5 leads this result

  • DRACO

    Claude Opus 5.5—
    Claude Sonnet 5.587.0%
    Source

    Not directly comparable

  • AutomationBench (Zapier 1.0.6)

    Claude Opus 5.5—
    Claude Sonnet 5.544.7%
    Source

    Not directly comparable

Coding

  • FrontierCode 1.1 Main

    Claude Opus 5.554.4%
    Source
    Claude Sonnet 5.546.2%
    Source

    Claude Opus 5.5 leads this result

  • cursorBench40

    Shared source
    Claude Opus 5.557.8%
    Claude Sonnet 5.555.5%

    Claude Opus 5.5 leads this result

  • SWE-bench Pro

    Claude Opus 5.589.9%
    Source
    Claude Sonnet 5.581.3%
    Source

    Claude Opus 5.5 leads this result

  • SWE Multilingual

    Claude Opus 5.593.9%
    Source
    Claude Sonnet 5.590.3%
    Source

    Claude Opus 5.5 leads this result

  • SWE Multimodal

    Claude Opus 5.561.4%
    Source
    Claude Sonnet 5.554.3%
    Source

    Claude Opus 5.5 leads this result

  • DeepSWE

    Claude Opus 5.574.2%
    Source
    Claude Sonnet 5.571.0%
    Source

    Claude Opus 5.5 leads this result

  • FrontierCode 1.1 Extended

    Claude Opus 5.563.6%
    Source
    Claude Sonnet 5.559.1%
    Source

    Claude Opus 5.5 leads this result

  • FrontierSWE v2

    Claude Opus 5.562.3%
    Source
    Claude Sonnet 5.561.9%
    Source

    Claude Opus 5.5 leads this result

  • ProgramBench

    Claude Opus 5.591.2%
    Source
    Claude Sonnet 5.579.7%
    Source

    Claude Opus 5.5 leads this result

Reasoning

  • ARC-AGI-1

    Claude Opus 5.597.50%
    Source
    Claude Sonnet 5.5—

    Not directly comparable

  • ARC-AGI-2

    Claude Opus 5.591.7%
    Source
    Claude Sonnet 5.5—

    Not directly comparable

Multimodal

  • Chartography (tools)

    Claude Opus 5.589.0%
    Source
    Claude Sonnet 5.590.2%
    Source

    Claude Sonnet 5.5 leads this result

  • Chartography (no tools)

    Claude Opus 5.564.4%
    Source
    Claude Sonnet 5.561.6%
    Source

    Claude Opus 5.5 leads this result

  • BenchCAD Vision2Code (no tools)

    Claude Opus 5.50.730
    Source
    Claude Sonnet 5.50.747
    Source

    Claude Sonnet 5.5 leads this result

  • BenchCAD Vision2Code (tools)

    Claude Opus 5.50.962
    Source
    Claude Sonnet 5.50.963
    Source

    Claude Sonnet 5.5 leads this result

  • Biomedical image analysis

    Claude Opus 5.571.4%
    Source
    Claude Sonnet 5.572.2%
    Source

    Claude Sonnet 5.5 leads this result

  • OfficeQA

    Claude Opus 5.578.9%
    Source
    Claude Sonnet 5.576.9%
    Source

    Claude Opus 5.5 leads this result

  • OfficeQA Pro

    Claude Opus 5.567.7%
    Source
    Claude Sonnet 5.565.6%
    Source

    Claude Opus 5.5 leads this result

Knowledge

  • HLE w/o tools

    Claude Opus 5.564.4%
    Source
    Claude Sonnet 5.556.9%
    Source

    Claude Opus 5.5 leads this result

  • HealthBench (raw)

    Claude Opus 5.568.1%
    Source
    Claude Sonnet 5.569.4%
    Source

    Claude Sonnet 5.5 leads this result

  • HealthBench (length-adjusted)

    Claude Opus 5.560.6%
    Source
    Claude Sonnet 5.565.4%
    Source

    Claude Sonnet 5.5 leads this result

  • HealthBench Professional

    Claude Opus 5.565.6%
    Source
    Claude Sonnet 5.569.2%
    Source

    Claude Sonnet 5.5 leads this result

  • HealthBench Professional (raw)

    Claude Opus 5.577.1%
    Source
    Claude Sonnet 5.577.1%
    Source

    Tie

  • BioMysteryBench (human-solvable)

    Claude Opus 5.589.3%
    Source
    Claude Sonnet 5.589.2%
    Source

    Claude Opus 5.5 leads this result

  • BioMysteryBench (human-difficult)

    Claude Opus 5.550.0%
    Source
    Claude Sonnet 5.544.7%
    Source

    Claude Opus 5.5 leads this result

  • SpatialBench Verified

    Claude Opus 5.572.0%
    Source
    Claude Sonnet 5.572.5%
    Source

    Claude Sonnet 5.5 leads this result

  • SingleCellBench

    Claude Opus 5.561.2%
    Source
    Claude Sonnet 5.559.1%
    Source

    Claude Opus 5.5 leads this result

  • Morphology-to-molecule matching

    Claude Opus 5.534.0%
    Source
    Claude Sonnet 5.525.0%
    Source

    Claude Opus 5.5 leads this result

  • Medicinal chemistry

    Claude Opus 5.563.5%
    Source
    Claude Sonnet 5.565.3%
    Source

    Claude Sonnet 5.5 leads this result

  • Protein Design

    Claude Opus 5.560.2%
    Source
    Claude Sonnet 5.551.0%
    Source

    Claude Opus 5.5 leads this result

  • Protein Design library ranking

    Claude Opus 5.556.0%
    Source
    Claude Sonnet 5.554.8%
    Source

    Claude Opus 5.5 leads this result

  • De novo protein-binder design

    Claude Opus 5.582.6%
    Source
    Claude Sonnet 5.582.3%
    Source

    Claude Opus 5.5 leads this result

  • Protocols (troubleshooting)

    Claude Opus 5.573.7%
    Source
    Claude Sonnet 5.567.3%
    Source

    Claude Opus 5.5 leads this result

  • Protocols (understanding)

    Claude Opus 5.569.0%
    Source
    Claude Sonnet 5.566.6%
    Source

    Claude Opus 5.5 leads this result

Multilingual

  • GMMLU

    Claude Opus 5.594.3%
    Source
    Claude Sonnet 5.592.1%
    Source

    Claude Opus 5.5 leads this result

  • MILU

    Claude Opus 5.593.1%
    Source
    Claude Sonnet 5.591.6%
    Source

    Claude Opus 5.5 leads this result

Math

  • ArXivMath Aug. 2026 (no tools)

    Claude Opus 5.591.2%
    Source
    Claude Sonnet 5.586.8%
    Source

    Claude Opus 5.5 leads this result

  • ArXivMath Aug. 2026 (tools)

    Claude Opus 5.596.9%
    Source
    Claude Sonnet 5.595.2%
    Source

    Claude Opus 5.5 leads this result

51 public results · 45 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Claude Opus 5.5 vs Claude Sonnet 5.5

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.

Last updated September 28, 2026