Claude Sonnet 5.5 (xHigh): benchmark results
Provider: Anthropic. Released 2026-09-28. Access: API.
Unified ELO 1929 ± 25, rank #30 of 2059 rated models, from 30 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LiveBench Code Generation | 92.96 | Score | 98.5 |
| LiveBench Integrals With Game | 100 | Score | 96.9 |
| Epoch AI - Critpt | 31.14 | Score | 96.5 |
| LiveBench Consecutive Events | 90.94 | Score | 95.4 |
| CursorBench 4.0 | 53.1 | Score (%) | 95 |
| LiveBench Simplify | 72.37 | Score | 93.8 |
| Bug Hunt Bench - LMS | 20 | Planted Bugs Fixed (out of 60) | 91.1 |
| LLM2014 Logic 2026-09 | 66.5 | Median Score | 90.9 |
| LiveBench Code Completion | 84.78 | Score | 90.8 |
| Bug Hunt Bench | 36 | Planted Bugs Fixed (out of 105) | 90.1 |
| LiveBench Zebra Puzzle | 100 | Score | 86.2 |
| Bug Hunt Bench - VS Code Extension | 16 | Planted Bugs Fixed (out of 45) | 84.9 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-5-xhigh · How It Works · Data refreshed daily, snapshot 2026-09-30.