Metadata
| Source Table | benchmark_results |
| Source ID | DrtKMMtM7g |
| Parent | OSWorld |
| Children | — |
| Created | Apr 24, 2026, 6:42 PM |
| Updated | Apr 24, 2026, 6:42 PM |
| Synced | Apr 24, 2026, 6:42 PM |
Record Data
id | DrtKMMtM7g |
benchmarkId | Hpb8OjdhT9 |
modelId | Claude Haiku 4.5(ai-model) |
score | 50.7 |
unit | percent |
date | 2025-10-15 |
sourceUrl | — |
notes | OSWorld-Verified computer-use benchmark. Outperforms Sonnet 4 (42.2%) and far exceeds Sonnet 3.5 (14%). Reported by Anthropic at release. |
Source Check Verdicts
unverifiable95% confidence
Last checked: 4/24/2026
Inline sourcing: unverifiable
Debug info
Thing ID: DrtKMMtM7g
Source Table: benchmark_results
Source ID: DrtKMMtM7g
Parent Thing ID: Hpb8OjdhT9