Claude Haiku 5.5 (High): benchmark results
Provider: Anthropic. Access: API.
Unified ELO 1822 ± 14, rank #103 of 2131 rated models, from 102 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA GDP.pdf - HR - Criterion Pass Rate | 84.12 | Criterion Pass Rate (%) | 94.3 |
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | 70 | Omniscience Index | 92.3 |
| AA GDP.pdf - Legal - Criterion Pass Rate | 84.17 | Criterion Pass Rate (%) | 91.4 |
| AA-Omniscience Index - Software Engineering (SWE) - Rust | 70 | Omniscience Index | 90.6 |
| AA-Omniscience Index - Software Engineering (SWE) - Dart | 42 | Omniscience Index | 89.9 |
| AA-Omniscience Index - Software Engineering (SWE) - Kotlin | 46 | Omniscience Index | 89.9 |
| WebDev Arena (Gaming) | 1706 | Arena Score | 89.9 |
| AA-Omniscience Index - Software Engineering (SWE) - TypeScript | 58.89 | Omniscience Index | 89.5 |
| AA CritPt | 18.57 | Accuracy (%) | 88.9 |
| Artificial Analysis Intelligence Index | 37.82 | Intelligence Index | 88.9 |
| AA-Omniscience Index - Software Engineering (SWE) | 48.7 | Omniscience Index | 87.9 |
| AA-Omniscience Index - Software Engineering (SWE) - Go | 56 | Omniscience Index | 87.7 |
Interactive version: theaggregate.ai/model?slug=claude-haiku-5-5-high · How It Works · Data refreshed daily, snapshot 2026-10-09.