BlogLLM Benchmark Scores as Published, Side by Side
Malicious computer use (Anthropic internal): Results as Published
Every result the catalog holds for Malicious computer use (Anthropic internal): 6 models from 1 developer, read from 2 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Safety and AlignmentMaintainer Anthropic (internal evaluation)Introduced 2026Data version 2026103001, as of 2026-10-30
112 tasks in a sandbox with GUI and CLI computer-use tools across surveillance, harmful content and scaled abuse; refusal rate without mitigations.
Malicious computer use refusal rate (without mitigations)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Haiku 5.5Anthropic, released 2026-10-07 | 82.59% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 79.46% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19; printed on 1 more page | - |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 79.46% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19; printed on 1 more page | - |
| Claude Mythos 5.1Anthropic, released 2026-09-01 | 87.5% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19; printed on 1 more page | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 84.68% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | - |
| Claude Haiku 4.5Anthropic, released 2025-10-15 | 58.93% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.