Claude Opus 5.5
ReleasedModel Claude Opus 5.5 is a model by Anthropic, released on 22 Sept 2026 (23 days ago).
In the Frontier SetAnthropic positions this model in its top tier — role: Work & coding. “For long-running agentic coding and knowledge work” Source: platform.claude.com · checked on 4 Oct 2026
- Where can it be used?
- Evidenced as usable in: Claude, Claude Code, Claude Enterprise, Claude Team, GitHub CopilotFor 9 more recorded products there is no statement; that does not mean “not available”.Available in the provider’s API
- Did we test it?
- No lab run published yet
- Last change
- 23 days ago
- Evidence
- 6 sources from 3 sitesRegistry entry:
What backs this up?
Three kinds of evidence, kept apart. None of them proves AGI on its own; where one is missing, the page says so.
- In real productsEvidenced as usable in: Claude, Claude Code, Claude Enterprise, Claude Team, GitHub Copilot
- agi.jetzt PrüfstandNo published run yet.
- Public benchmarks25 reported results on 17 benchmarks — each with its source
A model and the product around it are different things: a result for one does not carry over to the other.
Public benchmark results
Results reported by benchmark maintainers or providers, each with its source. They are not averaged and not compared across benchmarks; a provider result is self-reported. Some sources are data files of the benchmark’s own site rather than pages; they are marked as machine-readable.
- Claude Opus 5.566.3 %Chartography · v1 · accuracy (expert-range graded), no toolssource as of 03/10/2026 · benchmark maintainer · mode not stated · judge: google/gemini-3.5-flash · tools: no · setting: Inspect AI (surge-ai/chartography) · attempts: 10 · web: no · reasoning: Adaptive thinking, max effort · computer use: no · reported as „Claude Opus 5.5 (Adaptive/Max)“Source: surgehq.ai — Chartography, Claude Opus 5.5
- Claude Opus 5.530.6 %GDP.pdf · v1 · pass rate, all criteria (strict)source as of 03/10/2026 · benchmark maintainer · mode not stated · judge: google/gemini-3.5-flash · tools: no · setting: Inspect AI (surge-ai/gdp-pdf) · attempts: 5 · web: no · reasoning: Adaptive thinking, max effort · computer use: no · reported as „Claude Opus 5.5 (Adaptive/Max)“Source: surgehq.ai — GDP.pdf, Claude Opus 5.5
- Claude Opus 5.5$9,235.25Vending-Bench 2 · 2 · final bank balancesource as of 03/10/2026 · benchmark maintainer · model + harness · Andon Labs Vending-Bench 2 agent environment (email, web search, inventory tools, notes/reminders) · tools: yes · budget: ~1 simulated year; 3000-6000 messages, 60-100M output tokens per run · attempts: 6 · web: yesMachine-readable source: andonlabs.com · data bundle of the website, not linked
- Claude Opus 5.591.67 %ARC-AGI-2 · semi-private · accuracy (task pass rate)source as of 02/10/2026 · benchmark maintainer · mode not stated · reasoning: max · reported as „Claude Opus 5.5 (Max)“Machine-readable source: arcprize.org · JSON — ARC-AGI-2, Claude Opus 5.5
- Claude Opus 5.554.6 %FrontierCode · 1.1-main · overall score (mergeability)source as of 29/09/2026 · benchmark maintainer · mode not stated · judge: model-graded rubric checks (grader not named on leaderboard) · tools: yes · web: yesSource: cognition.com — FrontierCode, Claude Opus 5.5
- Claude Opus 5.588.4 %SimpleBench · avg5 · accuracy (average of 5 runs)evaluated 24/09/2026 · benchmark maintainer · model alone · pass@k: AVG@5 · temperature: 0.7 (top-p 0.95)Machine-readable source: simple-bench.com · JavaScript file — SimpleBench, Claude Opus 5.5
- Claude Opus 5.50.58AA-Omniscience (net score) · public-split · net score (correct − incorrect)source as of 22/09/2026 · self-reported by the provider · model alone · web: noSource: www-cdn.anthropic.com · PDF — AA-Omniscience (net score), Claude Opus 5.5
- Claude Opus 5.573 %BenchCAD Vision2Code · v1 · voxel IoU, no toolssource as of 22/09/2026 · self-reported by the provider · mode not stated · tools: no · setting: Anthropic internal; random 1,000-file subset of 17,900 Vision2Code files; 256x256 px views (corrected) · attempts: 5 · reasoning: adaptive thinking, max effortSource: www-cdn.anthropic.com · PDF — BenchCAD Vision2Code, Claude Opus 5.5
- Claude Opus 5.596.2 %BenchCAD Vision2Code · v1 · voxel IoU, with toolssource as of 22/09/2026 · self-reported by the provider · mode not stated · tools: yes · setting: Anthropic internal; random 1,000-file subset of 17,900 Vision2Code files; 256x256 px views (corrected) · attempts: 5 · reasoning: adaptive thinking, max effortSource: www-cdn.anthropic.com · PDF — BenchCAD Vision2Code, Claude Opus 5.5
- Claude Opus 5.589 %Chartography · v1 · accuracy (expert-range graded), with toolssource as of 22/09/2026 · self-reported by the provider · mode not stated · judge: Gemini 3.5 Flash · tools: yes · setting: Anthropic internal implementation of Chartography · attempts: 5 · web: no · reasoning: adaptive thinking, max effort · computer use: noSource: www-cdn.anthropic.com · PDF — Chartography, Claude Opus 5.5
- Claude Opus 5.574.2 %DeepSWE · 1.1 · mean score (5 trials)source as of 22/09/2026 · self-reported by the provider · mode not stated · tools: yes · attempts: 5 · reasoning: adaptive thinking, max effort (card default) · temperature: default samplingSource: www-cdn.anthropic.com · PDF — DeepSWE, Claude Opus 5.5
- Claude Opus 5.595 %FrontierMath Tier 4 · v2 · accuracy (mean score)evaluated 22/09/2026 · benchmark maintainer · mode not stated · tools: yes · budget: 1,000,000 tokens hard limit (forced submission at 660,000) · setting: Epoch AI FrontierMath implementation (Inspect): python tool + submit_answer tool · web: no · reasoning: max · reported as „claude-opus-5-5_max“Machine-readable source: epoch.ai · ZIP download — FrontierMath Tier 4, Claude Opus 5.5
Show 13 more
- Claude Opus 5.591.23 %FrontierMath Tiers 1–3 · v2 · accuracy (mean score)evaluated 22/09/2026 · benchmark maintainer · mode not stated · tools: yes · budget: 1,000,000 tokens hard limit (forced submission at 660,000) · setting: Epoch AI FrontierMath implementation (Inspect): python tool + submit_answer tool · web: no · reasoning: max · reported as „claude-opus-5-5_max“Machine-readable source: epoch.ai · ZIP download — FrontierMath Tiers 1–3, Claude Opus 5.5
- Claude Opus 5.554.6 %HLE-Diamond · 2026-09-22 · accuracysource as of 22/09/2026 · benchmark maintainer · model alone · web: no · reasoning: highSource: lastexam.ai — HLE-Diamond, Claude Opus 5.5
- Claude Opus 5.560.9 %HLE-Diamond · 2026-09-22 · accuracysource as of 22/09/2026 · benchmark maintainer · model alone · web: no · reasoning: maxSource: lastexam.ai — HLE-Diamond, Claude Opus 5.5
- Claude Opus 5.562.4 %HLE-Diamond · 2026-09-22 · accuracy · reasoning halfsource as of 22/09/2026 · benchmark maintainer · model alone · subset: reasoning partition (500 questions) · web: no · reasoning: highSource: lastexam.ai — HLE-Diamond, Claude Opus 5.5
- Claude Opus 5.573.9 %HLE-Diamond · 2026-09-22 · accuracy · toolssource as of 22/09/2026 · benchmark maintainer · model + harness · Claude Code 2.1.280 · tools: yes · web: yes · reasoning: highSource: lastexam.ai — HLE-Diamond, Claude Opus 5.5
- Claude Opus 5.581.8 %OSWorld · 2.0-2026-09-10-tasks · partial scoresource as of 22/09/2026 · self-reported by the provider · model + harness · Anthropic computer-use harness (retains all screenshots; server-side context compaction at 100k tokens) · judge: Claude Opus 4.8 (for model-graded tasks) · tools: yes · budget: 500 action steps, 1080p · attempts: 5 · reasoning: max effort · computer use: yesSource: www-cdn.anthropic.com · PDF — OSWorld, Claude Opus 5.5
- Claude Opus 5.548.7 %OSWorld · 2.0-2026-09-10-tasks · strict pass rate (all checkpoints)source as of 22/09/2026 · self-reported by the provider · model + harness · Anthropic computer-use harness with server-side compaction · judge: Claude Opus 4.8 · tools: yes · budget: 500 action steps · attempts: 5 · reasoning: max effort · computer use: yesSource: www-cdn.anthropic.com · PDF — OSWorld, Claude Opus 5.5
- Claude Opus 5.561.4 %SWE-bench Multimodal · v1 · resolve ratesource as of 22/09/2026 · self-reported by the provider · mode not stated · tools: yes · attempts: 5 · reasoning: adaptive thinking, max effortSource: www-cdn.anthropic.com · PDF — SWE-bench Multimodal, Claude Opus 5.5
- Claude Opus 5.589.9 %SWE-bench Pro · provider-unspecified · resolve ratesource as of 22/09/2026 · self-reported by the provider · mode not stated · tools: yes · attempts: 5 · reasoning: adaptive thinking, max effort · temperature: default samplingSource: www-cdn.anthropic.com · PDF — SWE-bench Pro, Claude Opus 5.5
- Claude Opus 5.566.4 %Terminal-Bench · 4.0 · task success ratesource as of 22/09/2026 · self-reported by the provider · mode not stated · tools: yes · attempts: 5 · reasoning: adaptive thinking, xhigh effortSource: www.anthropic.com — Terminal-Bench, Claude Opus 5.5
- Claude Opus 5.564.4 %Humanity's Last Exam · provider-run · accuracy · adaptive thihistoricalself-reported by the provider · model alone · judge: Claude Opus 4.6 · budget: 1M token cap · web: no · reasoning: thinking autoSource: www-cdn.anthropic.com · PDF — Humanity's Last Exam, Claude Opus 5.5
- Claude Opus 5.567.7 %Humanity's Last Exam · provider-run · accuracy · tools adaptive thihistoricalself-reported by the provider · model + harness · web search, web fetch, programmatic tool calling, code execution; HLE-source blocklist · judge: Claude Opus 4.6 · tools: yes · budget: 1M token cap · web: yes · reasoning: thinking autoSource: www-cdn.anthropic.com · PDF — Humanity's Last Exam, Claude Opus 5.5
- Claude Opus 5.564.85 %Terminal-Bench · 4.0 · accuracyhistoricalbenchmark maintainer · model + harness · Claude Code · reasoning: max · reported as „Opus 5.5“Source: www.tbench.ai — Terminal-Bench, Claude Opus 5.5
Where can it be used?
Only recorded availability statements are shown. A missing plan or surface means unknown, not unavailable. Where it applies only to a plan or a region, the row says so. “Rolling out” is not “available”. “Rollout reported” means a rollout was reported, but nothing has supported it for more than 90 days.
| Product | Status | since | Checked | Sources |
|---|---|---|---|---|
| ClaudeApp | Limited availability | not documented | checked 11 Oct 2026 | 1support.claude.com |
| ClaudeApp · Max 20x | Limited availability | not documented | ||
| ClaudeApp · Max 5x | Limited availability | not documented | ||
| ClaudeApp · Pro | Limited availability | not documented | ||
| Claude CodeCode | Limited availability | not documented | checked 11 Oct 2026 | 1support.claude.com |
| Claude EnterpriseWork · Enterprise | Limited availability | not documented | ||
| Claude TeamWork · Team | Limited availability | not documented | ||
| GitHub CopilotCopilot · Business | Limited availability | not documented | checked 11 Oct 2026 | 1docs.github.com |
| GitHub CopilotCopilot · Enterprise | Limited availability | not documented | checked 11 Oct 2026 | 1docs.github.com |
| GitHub CopilotCopilot · Max | Limited availability | not documented | checked 11 Oct 2026 | 1docs.github.com |
| GitHub CopilotCopilot · Pro Plus | Limited availability | not documented | checked 11 Oct 2026 | 1docs.github.com |
| GitHub Copilot | Limited availability | not documented | checked 11 Oct 2026 | 1docs.github.com |
Where a start is “not documented”, a source check found the state in place; the source names no start date.
No statement on record for 9 further products: ChatGPT, ChatGPT Work, Codex, Gemini, Gemini for Google Workspace, Grok, Langdock, Le Chat Enterprise, Microsoft 365 Copilot. No statement is not the same as not available.
Developer APIs
Developer access — not a statement about any work product.
| Product | Status | since | Checked | Sources |
|---|---|---|---|---|
| Claude APIAPI | Available | not documented | checked 3 Oct 2026 | 1platform.claude.com |
What did we test?
No lab run of Claude Opus 5.5 is published yet.
Nothing is shown until a real run exists. See what the lab tests:
Lifecycle and history
The dates the provider confirmed, and every recorded period of availability. A current period shows its checked status; one without a source check is marked not verified.
Announced—not recorded
Released
Deprecated—not recorded
Retired—not recorded
What changed?
Sourced changes concerning this model, newest first.
- 23 days agoadded to the record on 30 Sept 2026
1platform.claude.com
Evidence
Every source document behind the facts on this page, by domain.
| Domain | Docs | Documents |
|---|---|---|
| support.claude.com | 3 | |
| platform.claude.com | 2 | |
| docs.github.com | 1 |