BlogLLM Benchmark Scores as Published, Side by Side
CyScenarioBench: Results as Published
Every result the catalog holds for CyScenarioBench: 6 models from 1 developer, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area CybersecurityMaintainer Irregular (as named in the system card)Introduced 2026Data version 2026103001, as of 2026-10-30
CyScenarioBench tests whether a model can plan and run multi-stage cyber operations under realistic constraints: branching decisions, adherence to constraints and recovery from errors across dependent stages. The card reports the overall solve rate.
Not checked against a maintainer's page.
CyScenarioBench
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Haiku 5.5Anthropic, released 2026-10-07 | 3.3% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 46.1% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 67.6% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
| Claude Mythos 5.1Anthropic, released 2026-09-01 | 61.7% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 0.7% | Anthropic, Claude Haiku 5.5 System Cardchecked 2026-10-19 | - |
| Claude Haiku 4.5Anthropic, released 2025-10-15 | 0% | 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.