Public KG record
Claude Sonnet 5.5
Recorded overview
KG-recorded model related to Claude Sonnet 5.5; detailed English notes are not yet available.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: Terminal-Bench 4.0：70.6%
- Benchmarks: CursorBench 4.0：55.5%
- Benchmarks: FrontierCode 1.1：52.1%（Xhigh）、46.2%（Max）
- Benchmarks: OSWorld 2.1：80.1%
- Benchmarks: 植入缺陷测试发现55.5个缺陷
- Benchmarks: Code Arena WebDev排名第4、分数1699
- Benchmarks: LiveNewsBench 得分 86.38%，每题 $0.0920
- Benchmarks: CursorBench 4.0
Evidence coverage
The KG currently records 14 known information dimensions and has 5 undocumented dimensions, linked to 7 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- OmniParseBench — evaluated on
- Anthropic — develops
- Anthropic — improves
- Anthropic — releases
- Claude Fable 5 — uses