# Claude Sonnet 5 Benchmark Scores & Performance

> Claude Sonnet 5 by Anthropic scores 66.99/100 overall, ranking #23 out of 514 AI models.

Canonical page: https://benchlm.ai/models/claude-sonnet-5

Last updated: September 29, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Anthropic |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 1M |
| Overall Score | 66.99/100 |
| Overall Rank | #23 of 514 |

## Family & Coverage

- Family: Claude Sonnet 5
- Variant: base
- Benchmarks covered: 43 of 486
- Related earlier model: [Claude Sonnet 4.6](/models/claude-sonnet-4-6)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Terminal-Bench 3.0](/benchmarks/terminal-bench-3) | 14.6% |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 80.4% |
| [BrowseComp](/benchmarks/browsecomp) | 84.7% |
| [HLE w/ tools](/benchmarks/hlewithtools) | 57.4% |
| [OSWorld-Verified](/benchmarks/osworld-verified) | 81.2% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 1603 |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 47.5% |
| [Terminal-Bench 2.1 (Vals)](/benchmarks/valsterminalbench21) | 74.5% |
| [AA Agentic Index](/benchmarks/aaagenticindex) | 44.3% |
| [AA-AnalystAgent](/benchmarks/aaanalystagent) | 46.3% |
| [ApprenticeBench](/benchmarks/apprenticebench) | 16% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 85.2% |
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 63.2% |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 78.3% |
| [SWE Multimodal](/benchmarks/swe-bench-multimodal) | 28.1% |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 80.4% |
| [FrontierCode 1.1 Main](/benchmarks/frontiercode) | 42.7% |
| [CursorBench 3.2](/benchmarks/cursorbench32) | 61.5% |
| [AA-SciCode](/benchmarks/aascicode) | 54.3% |
| [VulcanBench CII v1](/benchmarks/vulcanciiv1) | 89.2% |
| [LiveCodeBench (Vals)](/benchmarks/valslivecodebench) | 82.4% |
| [SWE-bench (Vals)](/benchmarks/valsswebench) | 79.6% |
| [AA Coding Index](/benchmarks/aacodingindex) | 71.5% |
| [CursorBench 4.0](/benchmarks/cursorbench40) | 34.1% |

## Multimodal & Grounded Benchmarks

| Benchmark | Score |
|-----------|-------|
| [CharXiv](/benchmarks/charxiv) | 88.3% |
| [CharXiv w/o tools](/benchmarks/charxivnotools) | 77% |
| [AA-MMMU-Pro](/benchmarks/aammmupro) | 77.3% |
| [Design Arena Website](/benchmarks/designarenawebsite) | 1284 |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 82.0% |
| [CritPt](/benchmarks/critpt) | 16.9% |
| [MLCR-AA](/benchmarks/aamlcr) | 55.0% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [HLE](/benchmarks/hle) | 57.4% |
| [HLE w/o tools](/benchmarks/hlenotools) | 43.2% |
| [HLE-Verified](/benchmarks/hleverified) | 31.0% |
| [LABBench2](/benchmarks/labbench2) | 80.1% |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 38.2% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 91.1% |
| [AA-HLE](/benchmarks/aahle) | 41.3% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | 16.5% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 40.1% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 39.4% |
| [GPQA Diamond (Vals)](/benchmarks/valsgpqadiamond) | 88.9% |
| [MMLU-Pro (Vals)](/benchmarks/valsmmlupro) | 87.5% |

## Other Anthropic Models

- [Claude Opus 5.5](/models/claude-opus-5-5) - Score: 87.06
- [Claude Fable 5.1](/models/claude-fable-5-1) - Score: 82.97
- [Claude Sonnet 5.5](/models/claude-sonnet-5-5) - Score: 80.48
- [Claude Opus 5](/models/claude-opus-5) - Score: 79.65
- [Claude Fable 5](/models/claude-fable) - Score: 78.9
- [Claude Opus 4.8](/models/claude-opus-4-8) - Score: 70.41
- [Claude Opus 4.7 (Adaptive)](/models/claude-opus-4-7-adaptive) - Score: 68.54
- [Claude Opus 4.7](/models/claude-opus-4-7) - Score: 66.3
- [Claude Opus 4.6](/models/claude-opus-4-6) - Score: 63.62
- [Claude Sonnet 4.6](/models/claude-sonnet-4-6) - Score: 56.29
- [Claude Opus 4.5](/models/claude-opus-4-5) - Score: 55.04
- [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking) - Score: 54.97
- [Claude Sonnet 4.5](/models/claude-sonnet-4-5) - Score: 47.87
- [Claude Haiku 4.5](/models/claude-haiku-4-5) - Score: 42.49
- [Claude 4.1 Opus](/models/claude-4-1-opus) - Score: 38.46
- [Claude 4.1 Opus Thinking](/models/claude-4-1-opus-thinking) - Score: 36.6
- [Claude 4 Sonnet](/models/claude-4-sonnet) - Score: 36.09
- [Claude 3.5 Sonnet](/models/claude-3-5-sonnet) - Score: 30.03
- [Claude 3 Opus](/models/claude-3-opus) - Score: 28.68
- [Claude 3 Haiku](/models/claude-3-haiku) - Score: 14.81
- [Claude Mythos 5](/models/claude-mythos-5) - Score: not computed
- [Claude Opus 4.6 (Adaptive)](/models/claude-opus-4-6-thinking) - Score: not computed
- [Claude Mythos 5.1](/models/claude-mythos-5-1) - Score: not computed
- [Claude Mythos Preview](/models/claude-mythos-preview) - Score: not computed
- [Claude Haiku 4.5 Thinking](/models/claude-haiku-4-5-thinking) - Score: not computed
- [Claude Sonnet 4.5 Thinking](/models/claude-sonnet-4-5-thinking) - Score: not computed