Claude Haiku 5.5 (Low): benchmark results
Provider: Anthropic. Access: API.
Unified ELO 1770 ± 14, rank #194 of 2131 rated models, from 88 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-Omniscience Index - Software Engineering (SWE) - Rust | 80 | Omniscience Index | 95.9 |
| AA-Omniscience Index - Software Engineering (SWE) - Go | 66 | Omniscience Index | 91.8 |
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | 63.64 | Omniscience Index | 90.1 |
| AA-Omniscience Index - Software Engineering (SWE) - Julia | 36 | Omniscience Index | 88.2 |
| AA-Omniscience Index - Software Engineering (SWE) - Dart | 36 | Omniscience Index | 87.5 |
| AA-Omniscience Index - Software Engineering (SWE) - TypeScript | 55.56 | Omniscience Index | 87.4 |
| AA-Omniscience Index - Software Engineering (SWE) | 45.1 | Omniscience Index | 86 |
| AA-Omniscience Index - Software Engineering (SWE) - Python | 50 | Omniscience Index | 85.8 |
| AA-Omniscience Index - Software Engineering (SWE) - Java | 11 | Omniscience Index | 84.8 |
| AA-Omniscience Index - Software Engineering (SWE) - C | 61 | Omniscience Index | 83.9 |
| AA-Omniscience Hallucination Rate | 44.94 | Hallucination Rate (%) | 83.5 |
| AA-Omniscience Index - Software Engineering (SWE) - Kotlin | 32 | Omniscience Index | 82.6 |
Interactive version: theaggregate.ai/model?slug=claude-haiku-5-5-low · How It Works · Data refreshed daily, snapshot 2026-10-09.