Claude Haiku 5.5 (off): benchmark results
Provider: Anthropic. Access: API.
Aggregate Rating 1723 ± 37, rank #256 of 10916 rated models, from 4 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Conceptual Reasoning Index - Consistency (ACCoRD) | 75.38 | Chance-Corrected Score (0-100) | 71.9 |
| Conceptual Reasoning Index - Argument Evaluation (LMCA) | 39.26 | Chance-Corrected Score (0-100) | 52.7 |
| Conceptual Reasoning Index | 50.37 | Chance-Corrected Score (0-100) | 41.9 |
| Conceptual Reasoning Index - Decision Theory (DTBench) | 58.67 | Chance-Corrected Score (0-100) | 40.3 |
Interactive version: theaggregate.ai/model?slug=claude-haiku-5-5-off · How It Works · Data refreshed daily, snapshot 2026-11-08.