Claude Haiku 4.5 (20251001) (Thinking): benchmark results
Claude Haiku 4.5 (20251001) evaluated with thinking enabled. Provider: Anthropic. Released 2025-10-15. Access: API.
Aggregate Rating 1603 ± 20, rank #702 of 2168 rated models, from 47 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Writing | 49.08 | Writing Score | 86.2 |
| UGI - Natural Intelligence | 36.76 | NatInt Score | 83.5 |
| Vals AI MGSM | 92.15 | Accuracy (%) | 71.8 |
| Vals AI MedScribe | 85.23 | Accuracy (%) | 71.1 |
| AIME | 82.71 | Score (%) | 54.7 |
| Vals AI AIME | 82.71 | Accuracy (%) | 54.7 |
| CorpFin v2 | 60.61 | Score (%) | 52 |
| LegalBench | 81.24 | Score (%) | 50 |
| Vals AI CorpFin v2 | 60.61 | Accuracy (%) | 49.6 |
| MortgageTax | 62.16 | Score (%) | 47.2 |
| Vals AI Terminal-Bench 2.0 | 38.2 | Accuracy (%) | 46.2 |
| Vals AI CaseLaw v2 | 56.48 | Accuracy (%) | 45.8 |
Interactive version: theaggregate.ai/model?slug=claude-haiku-4-5-20251001-thinking · How It Works · Data refreshed daily, snapshot 2026-10-20.