BlogLLM Benchmark Scores as Published, Side by Side
Professional red-teamer prompt injection, browser use (Claude Cowork): Results as Published
Every result the catalog holds for Professional red-teamer prompt injection, browser use (Claude Cowork): 5 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
110 curated browser environments with injections seen through screenshots or page reads, run in the Claude Cowork harness; a programmatic checker decides success.
Browser use red-teamer attack success rate (attempt level)
lower is better
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Haiku 5.5Anthropic, released 2026-10-07 | 0% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 0% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19; printed on 1 more page | Effort: high; Setup as reported: Claude Cowork harness; 110 scenarios; 10 attempts per scenario; thinking enabled at high effort; with auto mode; scenarios with success 0/110 |
| 0% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Effort: high; Setup as reported: Claude Cowork harness; 110 scenarios; 10 attempts per scenario; thinking enabled at high effort; without safeguards; scenarios with success 0/110 | |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 0% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19; printed on 1 more page | - |
| Claude Fable 5.1Anthropic, released 2026-09-01 | 0% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19; printed on 1 more page | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 0% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Effort: high; Setup as reported: Claude Cowork harness; 110 scenarios; 10 attempts per scenario; thinking enabled at high effort; with auto mode; scenarios with success 0/110 |
| 0.37% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Effort: high; Setup as reported: Claude Cowork harness; 110 scenarios; 10 attempts per scenario; thinking enabled at high effort; without safeguards; scenarios with success 3/110 |
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.