Model comparison

Claude Opus 5.5 vs Claude Sonnet 5.5

Two Anthropic tiers compared on the figures that decide which one a workload actually needs.

Recorded profile verification October 1, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

Anthropic

Claude Opus 5.5

Frontier

Anthropic

Claude Sonnet 5.5

Balanced

AI model capability comparison
Specification	Claude Opus 5.5	Claude Sonnet 5.5
Provider
Provider	Anthropic	Anthropic
Tier
Tier	Frontier	Balanced
Context window
Context window	1M	1M
Max output
Max output	128K	128K
Input / 1M tokens
Input / 1M tokens	$4	Winner: $2
Output / 1M tokens
Output / 1M tokens	$20	Winner: $10
Weights
Weights	Closed	Closed
Parameters
Parameters	Not verifiedUnverified	Not verifiedUnverified
Reasoning levels
Reasoning levels	low, medium, high, xhigh, max	low, medium, high, xhigh, max
Modalities
Modalities	text, image	text, image
API model id
API model id	claude-opus-5-5	claude-sonnet-5-5
Released
Released	September 22, 2026	September 28, 2026
Artificial Analysis Intelligence Index [max] · source date Claude Opus 5.5: 2026-10-01
Artificial Analysis Intelligence Index [max] · source date Claude Opus 5.5: 2026-10-01	58	Not verifiedUnverified
Artificial Analysis Intelligence Index [max] · source date Claude Sonnet 5.5: 2026-10-01
Artificial Analysis Intelligence Index [max] · source date Claude Sonnet 5.5: 2026-10-01	Not verifiedUnverified	56
Humanity's Last Exam [max] · source date Claude Opus 5.5: 2026-09-26
Humanity's Last Exam [max] · source date Claude Opus 5.5: 2026-09-26	61.4	Not verifiedUnverified
Humanity's Last Exam · source date Claude Sonnet 5.5: 2026-10-01
Humanity's Last Exam · source date Claude Sonnet 5.5: 2026-10-01	Not verifiedUnverified	64.5
Terminal-Bench 4.0 [max] · source date Claude Opus 5.5: 2026-09-26, Claude Sonnet 5.5: 2026-10-01 (comparability not verified)
Terminal-Bench 4.0 [max] · source date Claude Opus 5.5: 2026-09-26, Claude Sonnet 5.5: 2026-10-01 (comparability not verified)	59.6	63.6
Terminal-Bench 4.0 [xhigh] · source date Claude Opus 5.5: 2026-09-22
Terminal-Bench 4.0 [xhigh] · source date Claude Opus 5.5: 2026-09-22	66.4	Not verifiedUnverified
Terminal-Bench 4.0 · source date Claude Sonnet 5.5: 2026-10-01
Terminal-Bench 4.0 · source date Claude Sonnet 5.5: 2026-10-01	Not verifiedUnverified	70.6
CursorBench 4.0 [max] · source date Claude Sonnet 5.5: 2026-10-01
CursorBench 4.0 [max] · source date Claude Sonnet 5.5: 2026-10-01	Not verifiedUnverified	55.5
FrontierCode 1.1 (Main) [xhigh] · source date Claude Sonnet 5.5: 2026-10-01
FrontierCode 1.1 (Main) [xhigh] · source date Claude Sonnet 5.5: 2026-10-01	Not verifiedUnverified	52.1
OSWorld 2.1 · source date Claude Sonnet 5.5: 2026-10-01
OSWorld 2.1 · source date Claude Sonnet 5.5: 2026-10-01	Not verifiedUnverified	80.1

Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

Source date2026-10-01
Anthropic (vendor-reported) (partial task set)
Source date2026-10-01
Anthropic (vendor-reported)
Source date2026-10-01
Anthropic (vendor-reported) (with tools)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
Source date2026-10-01
Cursor (vendor-run coding agent)
Source date2026-10-01
Artificial Analysis (independent, mini-swe-agent)
Agentic terminal work: long multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatDo not directly compare scores across Terminal-Bench versions: 4.0 revises and prunes the 3.0 task set and changes environment resources, requiring fresh trials. Within 4.0, harness, time limit, tools, sampling and resource settings must match; maintainer-agent and Artificial Analysis runs are not interchangeable.
Source date2026-10-01
Anthropic (vendor-reported)
Agentic terminal work: long multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatDo not directly compare scores across Terminal-Bench versions: 4.0 revises and prunes the 3.0 task set and changes environment resources, requiring fresh trials. Within 4.0, harness, time limit, tools, sampling and resource settings must match; maintainer-agent and Artificial Analysis runs are not interchangeable.
Source date2026-10-01
Artificial Analysis (Claude Sonnet 5.5 (max with fallback))
Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.
Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check the cited source and its date.
Source date2026-10-01
Artificial Analysis (Claude Opus 5.5 (max with fallback))
Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.
Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check the cited source and its date.
Source date2026-09-26
Artificial Analysis Terminal-Bench 4.0 (independent AA run, part of Intelligence Index v4.3.2)
Agentic terminal work: long multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatDo not directly compare scores across Terminal-Bench versions: 4.0 revises and prunes the 3.0 task set and changes environment resources, requiring fresh trials. Within 4.0, harness, time limit, tools, sampling and resource settings must match; maintainer-agent and Artificial Analysis runs are not interchangeable.
Source date2026-09-26
Artificial Analysis Humanity's Last Exam (independent, 2,158 text-only questions)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
Source date2026-09-22
Anthropic — Claude Opus 5.5 announcement (vendor-reported, xhigh; distinct effort/harness conditions from AA's independent 59.6)
Agentic terminal work: long multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatDo not directly compare scores across Terminal-Bench versions: 4.0 revises and prunes the 3.0 task set and changes environment resources, requiring fresh trials. Within 4.0, harness, time limit, tools, sampling and resource settings must match; maintainer-agent and Artificial Analysis runs are not interchangeable.

Pricing tiers

Claude Opus 5.5: Standard $4/$20 per MTok with no long-context surcharge. Cache reads $0.20; 5-minute writes $5 and 1-hour writes $8. Batch $2/$10. Fast research preview $8/$40 on the first-party Claude API only, not Batch. US-only inference adds 10% to all token categories where supported. Batch supports 300K output with output-300k-2026-03-24; standard output stays 128K. Knowledge cutoff Jun 2026; retirement not sooner than September 22, 2027.

Claude Sonnet 5.5: Standard $2/$10 per MTok with no long-context surcharge; cache reads $0.20, 5-minute writes $2.50 and 1-hour writes $4. Batch $1/$5. US-only inference adds 10% where supported. The 300K output limit requires the Batch API beta header output-300k-2026-03-24; standard output stays 128K. Knowledge cutoff Jun 2026; retirement not sooner than September 28, 2027.

FrontierRecord checked October 1, 2026

Claude Opus 5.5

Claude Opus 5.5 is Anthropic's recommended default for agentic coding and knowledge work. Anthropic reports performance near Fable 5.1 on most work and about 40% lower running cost than Opus 5 under its evaluation conditions. Artificial Analysis recorded an Intelligence Index v4.3.2 score of 58 at max effort with fallback in the October 1 capture.

Best for

Complex agentic coding
Enterprise knowledge work
Default frontier model

Watch out

Adaptive thinking cannot be disabled; forced tool use errors. Thinking blocks are tied to model/conversation, and computer_20251124 is rejected on Claude API/Google Cloud. Progress between tool calls can be hidden in empty thinking blocks unless display returns it. Effort defaults to medium; higher effort can increase token use.

BalancedRecord checked October 1, 2026

Claude Sonnet 5.5

Anthropic’s newer Sonnet model for everyday coding and knowledge work at the same $2/$10 token rates as Sonnet 5.

Best for

Everyday coding
Document and slide creation
Fast iteration

Watch out

Vendor scores use Anthropic's evaluation setup. between_tools turns off up-front thinking only at high effort or below. Forced tool use and non-default temperature/top_p/top_k error; older computer_20251124 and some advisors are rejected. Thinking blocks are model/conversation-bound; progress text needs a display setting that returns it. Haiku 5.5 is announced, not released as of October 1.

When the cheaper one wins

Claude Sonnet 5.5 is cheaper on output at $10 per million tokens against $20 for Claude Opus 5.5 — about 2.0×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. This compares standard short-context token rates, not total cost per accepted task. Include input, cache, context tiers, schedules, retries and review in your pilot.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

Pricing verified on both sides — Input and output rates are verified for both models.
4/5 core specs verified on both sides — Not published for at least one side: parameter count.
1 benchmark setup aligned with differing scores — Matched source, source date, units, effort and recorded run details: Artificial Analysis Intelligence Index.
Verified within the last 90 days — Older of the two catalog checks was 25 days ago.
Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Claude Opus 5.5: Claude model overview — whole-profile source check October 1 (accessed 2026-10-01)
Claude Opus 5.5: Claude current API pricing, caching and inference geography (accessed 2026-10-01)
Claude Opus 5.5: Anthropic — Claude Opus 5.5 (accessed 2026-09-26)
Claude Opus 5.5: Anthropic docs — Opus 5.5 overview (1M context, 128K output) (accessed 2026-09-26)
Claude Opus 5.5: Anthropic pricing (claude-opus-5-5 $4/$20, cache reads $0.20) (accessed 2026-09-26)
Claude Opus 5.5: Artificial Analysis — Intelligence Index v4.3.2 (dated score and effort variant) (accessed 2026-10-01)
Claude Opus 5.5: Anthropic selectable effort levels (separate from adaptive thinking mode) (accessed 2026-10-01)
Claude Sonnet 5.5: Claude model overview — whole-profile source check October 1 (accessed 2026-10-01)
Claude Sonnet 5.5: Claude current API pricing, caching and inference geography (accessed 2026-10-01)
Claude Sonnet 5.5: Anthropic release announcement (accessed 2026-10-01)
Claude Sonnet 5.5: Claude Platform Sonnet 5.5 specifications (accessed 2026-10-01)
Claude Sonnet 5.5: Claude models overview (accessed 2026-10-01)
Claude Sonnet 5.5: Anthropic selectable effort levels (separate from adaptive thinking mode) (accessed 2026-10-01)

Related comparisons

Diving deeper on one model? Claude Opus 5.5 · Claude Sonnet 5.5

Common questions

Claude Opus 5.5 vs Claude Sonnet 5.5

Answered from the verified figures on this page rather than general guidance.

Is Claude Opus 5.5 or Claude Sonnet 5.5 cheaper for input?

Claude Sonnet 5.5 is cheaper at $2 per million input tokens, against $4 for Claude Opus 5.5 — roughly 2.0× the price. Estimate both input and output token volume for your workload. These are base rates; Claude Opus 5.5: Standard $4/$20 per MTok with no long-context surcharge. Cache reads $0.20; 5-minute writes $5 and 1-hour writes $8. Batch $2/$10. Fast research preview $8/$40 on the first-party Claude API only, not Batch. US-only inference adds 10% to all token categories where supported. Batch supports 300K output with output-300k-2026-03-24; standard output stays 128K. Knowledge cutoff Jun 2026; retirement not sooner than September 22, 2027. Claude Sonnet 5.5: Standard $2/$10 per MTok with no long-context surcharge; cache reads $0.20, 5-minute writes $2.50 and 1-hour writes $4. Batch $1/$5. US-only inference adds 10% where supported. The 300K output limit requires the Batch API beta header output-300k-2026-03-24; standard output stays 128K. Knowledge cutoff Jun 2026; retirement not sooner than September 28, 2027.

Is Claude Opus 5.5 or Claude Sonnet 5.5 cheaper for output?

Claude Sonnet 5.5 is cheaper at $10 per million output tokens, against $20 for Claude Opus 5.5 — roughly 2.0× the price. Estimate both input and output token volume for your workload. These are base rates; Claude Opus 5.5: Standard $4/$20 per MTok with no long-context surcharge. Cache reads $0.20; 5-minute writes $5 and 1-hour writes $8. Batch $2/$10. Fast research preview $8/$40 on the first-party Claude API only, not Batch. US-only inference adds 10% to all token categories where supported. Batch supports 300K output with output-300k-2026-03-24; standard output stays 128K. Knowledge cutoff Jun 2026; retirement not sooner than September 22, 2027. Claude Sonnet 5.5: Standard $2/$10 per MTok with no long-context surcharge; cache reads $0.20, 5-minute writes $2.50 and 1-hour writes $4. Batch $1/$5. US-only inference adds 10% where supported. The 300K output limit requires the Batch API beta header output-300k-2026-03-24; standard output stays 128K. Knowledge cutoff Jun 2026; retirement not sooner than September 28, 2027.

Which has the larger context window, Claude Opus 5.5 or Claude Sonnet 5.5?

Both accept about 1M tokens of context, so document length will not decide between them.

Do Claude Opus 5.5 and Claude Sonnet 5.5 support the same reasoning levels?

Both expose these named effort settings: "low", "medium", "high", "xhigh", "max". The same labels do not guarantee equal compute budgets or behavior across providers. Compare quality, latency and cost on your own tasks.

Should I use Claude Opus 5.5 or Claude Sonnet 5.5?

We classify Claude Opus 5.5 in the frontier tier and Claude Sonnet 5.5 in the balanced tier. Test whether either meets your accuracy, tool-use and latency requirements before choosing on price.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

Input price: Claude Sonnet 5.5 costs $2 per 1M tokens versus $4 for Claude Opus 5.5 — a 2x difference at the headline tier.
Published Artificial Analysis Intelligence Index results differ: Claude Opus 5.5 scores 58 to 56 on the same listed benchmark, source attribution, source date, effort, and run variant (2026-10-01).
Positioning: Claude Opus 5.5 sits in the frontier tier, Claude Sonnet 5.5 in the balanced tier. Compare accuracy, reliability, latency, and cost on representative tasks before choosing.

Run the model picker Estimate stack cost All model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.