RankingClaude Sonnet 5.5
Claude Sonnet 5.5
Claude Sonnet 5.5 by Anthropic is a Claude Sonnet model, released 2026-09-28. This profile collects the published benchmark results and reported effort settings for this model. Configurations are compared on the effort page. Ranks are on the leaderboard.
10 published benchmark measures · 150 measured effort results · 3 benchmark families contribute across 2 task areas. 2 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →
Model evidence summary
This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →
Performance profile
Capabilities
Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.
Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.
Reported effort · Not specified
Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.
- Not specified: 12 observations
Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.
Inspect each result and its source ↓ · Download effort evidenceScore contributions and missing evidence
3 contributing families across 2 capabilities. Fixed reference panels do not change when the catalog expands.
Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.
Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.
Model information & shareable badge
- Lab
- Anthropic
- Catalog status
- active
- Availability
- Public provider catalog; account and region restrictions may apply
- Family
- Claude Sonnet
- Released
- 2026-09-28
- Context
- 1,000,000 tokens
- API list price
- $2 input / $10 output per million tokens
- License
- proprietary
- Model card
- https://platform.claude.com/docs/en/models/sonnet-5-5/overview
- Default Capability family coverage
/badge/claude-sonnet-5-5.svg
Claude Sonnet 5.5 measured results by effort setting
Each row is one published result for one effort setting. Evidence collected 2026-11-22. Compare the effort settings →
| Benchmark | Effort | Score | Source |
|---|---|---|---|
| AA-AnalystAgent | Max | 57.5% | Artificial Analysis |
| AA-Briefcase Elo | High | 1634 | Artificial Analysis |
| AA-Briefcase Elo | Low | 1268 | Artificial Analysis |
| AA-Briefcase Elo | Max | 1815 | Artificial Analysis |
| AA-Briefcase Elo | Medium | 1438 | Artificial Analysis |
| AA-Briefcase Elo | XHigh | 1739 | Artificial Analysis |
| AA-LCR v1.1 | High | 78.0% | Artificial Analysis |
| AA-LCR v1.1 | Low | 76.0% | Artificial Analysis |
| AA-LCR v1.1 | Max | 82.7% | Artificial Analysis |
| AA-LCR v1.1 | Medium | 76.3% | Artificial Analysis |
| AA-LCR v1.1 | XHigh | 79.7% | Artificial Analysis |
| AA-Omniscience Accuracy | High | 50.3% | Artificial Analysis |
| AA-Omniscience Accuracy | Low | 46.0% | Artificial Analysis |
| AA-Omniscience Accuracy | Max | 51.5% | Artificial Analysis |
| AA-Omniscience Accuracy | Medium | 45.8% | Artificial Analysis |
| AA-Omniscience Accuracy | XHigh | 50.9% | Artificial Analysis |
| AA-Omniscience Index | High | 18.7 | Artificial Analysis |
| AA-Omniscience Index | Low | 20.3 | Artificial Analysis |
| AA-Omniscience Index | Max | 30.5 | Artificial Analysis |
| AA-Omniscience Index | Medium | 18.6 | Artificial Analysis |
| AA-Omniscience Index | XHigh | 20.6 | Artificial Analysis |
| ARC-AGI-2 | High | 67.4% | ARC Prize |
| ARC-AGI-2 | Low | 24.0% | ARC Prize |
| ARC-AGI-2 | Medium | 32.8% | ARC Prize |
| ARC-AGI-2 | XHigh | 83.9% | ARC Prize |
| ARC-AGI-3 · provider-adapter | High | 35.5% | ARC Prize |
| ARC-AGI-3 · provider-adapter | Low | 0.6% | ARC Prize |
| ARC-AGI-3 · provider-adapter | Medium | 4.9% | ARC Prize |
| ARC-AGI-3 · provider-adapter | XHigh | 72.4% | ARC Prize |
| ARC-AGI-3 · standard | High | 1.2% | ARC Prize |
| ARC-AGI-3 · standard | Low | 0.4% | ARC Prize |
| ARC-AGI-3 · standard | Medium | 0.4% | ARC Prize |
| ARC-AGI-3 · standard | XHigh | 24.3% | ARC Prize |
| AutomationBench-AA | High | 59.4% | Artificial Analysis |
| AutomationBench-AA | Low | 49.4% | Artificial Analysis |
| AutomationBench-AA | Max | 71.8% | Artificial Analysis |
| AutomationBench-AA | Medium | 54.9% | Artificial Analysis |
| AutomationBench-AA | XHigh | 65.5% | Artificial Analysis |
| CritPt | High | 24.6% | Artificial Analysis |
| CritPt | Low | 11.4% | Artificial Analysis |
| CritPt | Max | 31.4% | Artificial Analysis |
| CritPt | Medium | 16.9% | Artificial Analysis |
| CritPt | XHigh | 31.1% | Artificial Analysis |
| FrontierCode 1.1 · extended-claude-code | High | 61.5% | Cognition |
| FrontierCode 1.1 · extended-claude-code | Low | 43.4% | Cognition |
| FrontierCode 1.1 · extended-claude-code | Max | 59.1% | Cognition |
| FrontierCode 1.1 · extended-claude-code | Medium | 50.5% | Cognition |
| FrontierCode 1.1 · extended-claude-code | XHigh | 64.4% | Cognition |
| FrontierCode 1.1 · main-claude-code | High | 49.4% | Cognition |
| FrontierCode 1.1 · main-claude-code | Low | 29.3% | Cognition |
| FrontierCode 1.1 · main-claude-code | Max | 46.2% | Cognition |
| FrontierCode 1.1 · main-claude-code | Medium | 36.5% | Cognition |
| FrontierCode 1.1 · main-claude-code | XHigh | 52.1% | Cognition |
| FrontierSWE v2 | Unspecified | 61.9% | Proximal |
| GDP.pdf: All-pass Rate | High | 25.2% | Artificial Analysis |
| GDP.pdf: All-pass Rate | Low | 16.0% | Artificial Analysis |
| GDP.pdf: All-pass Rate | Max | 25.8% | Artificial Analysis |
| GDP.pdf: All-pass Rate | Medium | 20.2% | Artificial Analysis |
| GDP.pdf: All-pass Rate | XHigh | 24.6% | Artificial Analysis |
| GDPval-AA v2.1 Leaderboard | High | 1551 | Artificial Analysis |
| GDPval-AA v2.1 Leaderboard | Low | 1182 | Artificial Analysis |
| GDPval-AA v2.1 Leaderboard | Max | 1838 | Artificial Analysis |
| GDPval-AA v2.1 Leaderboard | Medium | 1326 | Artificial Analysis |
| GDPval-AA v2.1 Leaderboard | XHigh | 1743 | Artificial Analysis |
| Harvey LAB-AA v1.1: Hallucination-Gated All-Pass Rate | Max | 2.8% | Artificial Analysis |
| HLE · full · Scale official evaluation | XHigh | 46.1% | Scale |
| HLE · text only · Scale official evaluation | XHigh | 46.6% | Scale |
| Humanity's Last Exam | High | 45.8% | Artificial Analysis |
| Humanity's Last Exam | Low | 36.2% | Artificial Analysis |
| Humanity's Last Exam | Max | 55.0% | Artificial Analysis |
| Humanity's Last Exam | Medium | 39.8% | Artificial Analysis |
| Humanity's Last Exam | XHigh | 50.0% | Artificial Analysis |
| LiveBench · AMPS Hard · 2026-06-25 | Max | 98.0% | LiveBench |
| LiveBench · AMPS Hard · 2026-06-25 | XHigh | 98.0% | LiveBench |
| LiveBench · code completion · 2026-06-25 | Max | 87.0% | LiveBench |
| LiveBench · code completion · 2026-06-25 | XHigh | 84.8% | LiveBench |
| LiveBench · code generation · 2026-06-25 | Max | 95.8% | LiveBench |
| LiveBench · code generation · 2026-06-25 | XHigh | 93.0% | LiveBench |
| LiveBench · connections · 2026-06-25 | Max | 99.3% | LiveBench |
| LiveBench · connections · 2026-06-25 | XHigh | 98.5% | LiveBench |
| LiveBench · consecutive events · 2026-06-25 | Max | 40.6% | LiveBench |
| LiveBench · consecutive events · 2026-06-25 | XHigh | 90.9% | LiveBench |
| LiveBench · integrals with game · 2026-06-25 | Max | 97.0% | LiveBench |
| LiveBench · integrals with game · 2026-06-25 | XHigh | 100.0% | LiveBench |
| LiveBench · javascript · 2026-06-25 | Max | 77.3% | LiveBench |
| LiveBench · javascript · 2026-06-25 | XHigh | 36.4% | LiveBench |
| LiveBench · logic with navigation · 2026-06-25 | Max | 82.0% | LiveBench |
| LiveBench · logic with navigation · 2026-06-25 | XHigh | 80.0% | LiveBench |
| LiveBench · math comp · 2026-06-25 | Max | 97.1% | LiveBench |
| LiveBench · math comp · 2026-06-25 | XHigh | 97.1% | LiveBench |
| LiveBench · olympiad · 2026-06-25 | Max | 92.5% | LiveBench |
| LiveBench · olympiad · 2026-06-25 | XHigh | 91.7% | LiveBench |
| LiveBench · paraphrase · 2026-06-25 | Max | 48.2% | LiveBench |
| LiveBench · paraphrase · 2026-06-25 | XHigh | 62.3% | LiveBench |
| LiveBench · plot unscrambling · 2026-06-25 | Max | 48.6% | LiveBench |
| LiveBench · plot unscrambling · 2026-06-25 | XHigh | 67.8% | LiveBench |
| LiveBench · python · 2026-06-25 | Max | 35.0% | LiveBench |
| LiveBench · python · 2026-06-25 | XHigh | 35.0% | LiveBench |
| LiveBench · simplify · 2026-06-25 | Max | 50.9% | LiveBench |
| LiveBench · simplify · 2026-06-25 | XHigh | 72.4% | LiveBench |
| LiveBench · spatial · 2026-06-25 | Max | 98.0% | LiveBench |
| LiveBench · spatial · 2026-06-25 | XHigh | 98.0% | LiveBench |
| LiveBench · story generation · 2026-06-25 | Max | 69.9% | LiveBench |
| LiveBench · story generation · 2026-06-25 | XHigh | 77.1% | LiveBench |
| LiveBench · summarize · 2026-06-25 | Max | 58.2% | LiveBench |
| LiveBench · summarize · 2026-06-25 | XHigh | 70.3% | LiveBench |
| LiveBench · tablejoin · 2026-06-25 | Max | 39.8% | LiveBench |
| LiveBench · tablejoin · 2026-06-25 | XHigh | 46.9% | LiveBench |
| LiveBench · tablereformat · 2026-06-25 | Max | 98.0% | LiveBench |
| LiveBench · tablereformat · 2026-06-25 | XHigh | 98.0% | LiveBench |
| LiveBench · theory of mind · 2026-06-25 | Max | 86.5% | LiveBench |
| LiveBench · theory of mind · 2026-06-25 | XHigh | 69.2% | LiveBench |
| LiveBench · typescript · 2026-06-25 | Max | 56.7% | LiveBench |
| LiveBench · typescript · 2026-06-25 | XHigh | 46.7% | LiveBench |
| LiveBench · typos · 2026-06-25 | Max | 86.0% | LiveBench |
| LiveBench · typos · 2026-06-25 | XHigh | 84.0% | LiveBench |
| LiveBench · zebra puzzle · 2026-06-25 | Max | 100.0% | LiveBench |
| LiveBench · zebra puzzle · 2026-06-25 | XHigh | 100.0% | LiveBench |
| LMArena Agent Arena | Max | 12.5 | LMArena |
| MaxxBench | Max | 66.9% | unLAP |
| MLCR-AA | High | 18.9% | Artificial Analysis |
| MLCR-AA | Low | 19.4% | Artificial Analysis |
| MLCR-AA | Max | 41.7% | Artificial Analysis |
| MLCR-AA | Medium | 17.8% | Artificial Analysis |
| MLCR-AA | XHigh | 20.6% | Artificial Analysis |
| SciCode | High | 53.7% | Artificial Analysis |
| SciCode | Low | 49.1% | Artificial Analysis |
| SciCode | Max | 61.0% | Artificial Analysis |
| SciCode | Medium | 52.9% | Artificial Analysis |
| SciCode | XHigh | 57.3% | Artificial Analysis |
| sudo L7 | Max | 41.7% | Surge AI |
| SWE-Bench Pro V2 Hard · mini-swe-agent | XHigh | 70.6% | Scale |
| Terminal-Bench 4.0 · claudecode | Max | 61.8% | Terminal-Bench |
| Terminal-Bench v4.0 | High | 43.9% | Artificial Analysis |
| Terminal-Bench v4.0 | Low | 20.7% | Artificial Analysis |
| Terminal-Bench v4.0 | Max | 63.6% | Artificial Analysis |
| Terminal-Bench v4.0 | Medium | 29.8% | Artificial Analysis |
| Terminal-Bench v4.0 | XHigh | 57.1% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | High | 34.3% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | Low | 10.5% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | Max | 53.3% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | Medium | 16.2% | Artificial Analysis |
| Terminal-Bench-Science 0.1 | XHigh | 52.4% | Artificial Analysis |
| Vals AI · Code Migration v1 | Max | 69.8% | Vals AI |
| Vals AI · Excel Modeling Benchmark v1 | Max | 75.7% | Vals AI |
| Vals AI · Finance Agent v2 | Max | 58.1% | Vals AI |
| Vals AI · Legal Research Bench v1 | Max | 48.1% | Vals AI |
| Vals AI · Tax Agent Bench v1: Weighted Pass | Max | 73.4% | Vals AI |
| Vals AI · Terminal-Bench 2.1 | High | 83.1% | Vals AI |
| Vals AI · Vibe Code Bench v1.1 | Max | 92.4% | Vals AI |
Benchmark scores & sources
Original results, evaluation harnesses, and evidence behind this model.
| Benchmark | Bucket | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|---|
| ARC-AGI-2 | Hard reasoning | 83.9% | ARC Prize verifiedcontributes to capability | official board | 2026-09-28 |
| AutomationBench-AA | Supporting evidence | 71.76882128193995% | Artificial Analysis AutomationBench-AA | official board | 2026-11-21 |
| Bug Hunt Bench | Supporting evidence | 48.86% | Bug Hunt Bench · max | official board | 2026-09-29 |
| Bug Hunt Bench | Supporting evidence | 34.29% | Bug Hunt Bench · xhigh | official board | 2026-09-29 |
| DAYJOB Finance | Supporting evidence | 40.5% | DAYJOB Finance · max | official board | 2026-11-20 |
| DAYJOB Healthcare | Supporting evidence | 34% | DAYJOB Healthcare · max | official board | 2026-11-20 |
| FrontierCS 2 | Supporting evidence | 50% | Claude Code | official board | 2026-11-20 |
| FrontierSWE v2 | Supporting evidence | 61.9% | Proximal FrontierSWE v2 · Proximus · unspecified | official board | 2026-11-22 |
| LMArena Agent Arena | Supporting evidence | 15.56 | LMArena Agent Arena · max | official board | 2026-11-18 |
| LMArena Agent Arena | Supporting evidence | 7.42 | LMArena Agent Arena · high | official board | 2026-11-18 |
| SWE-bench Pro | Coding | 70.59% | SWE-bench Pro reportedcontributes to capability | official board | 2026-10-12 |
| Terminal-Bench 4.0 | Coding | 61.82% | Terminal-Bench 4.0 reportedcontributes to capability | official board | 2026-09-28 |
| DeepSWE v1.1 | Agentic | — | — | — | — |
| GDPval-AA | Agentic | — | — | — | — |
| GPQA Diamond | Hard reasoning | — | — | — | — |
| Humanity's Last Exam | Hard reasoning | — | — | — | — |
| LiveCodeBench | Coding | — | — | — | — |
| LMArena Text Arena | Human pref | — | — | — | — |
| MMLU-Pro | Knowledge | — | — | — | — |
| OSWorld-Verified | Agentic | — | — | — | — |
| SWE-bench Verified | Agentic | — | — | — | — |
| Terminal-Bench 2.1 | Agentic | — | — | — | — |