Redwood Research
We track 5 benchmarks that Redwood Research made or helped make.
0 in use 4 with public code 3 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| LinuxArena AI-control setting in live Linux production-like environments. Measures stealthy side-task completion against action and CoT monitors. | Deception and alignment | Apr 2026 | 0% | System cards only |
| Subversion Strategy Eval Models must devise and execute strategies to subvert control protocols without shared memory between calls. | Deception and alignment | Dec 2024 | System cards only | |
| BashArena Agents do 637 Linux admin tasks while a red team tries four sabotage goals, such as exfiltrating secrets, past a monitor. Reports sabotage success and monitor catch rates. | Deception and alignment | Dec 2025 | 99.1% | System cards only |
| ACCoRD Models state probabilities and preferences on conceptual questions, and the benchmark checks 567 expert-approved logical consistency constraints such as conjunction rules and order invariance. | Other | Aug 2026 | 89.4 | Not in cards |
| Conceptual Reasoning Index An index that ranks models on reasoning about hard-to-verify topics such as AI alignment and decision theory. It weights LMCA 60 percent and ACCoRD and DTBench 20 percent each. | Composite indices | Aug 2026 | 79.0 | Not in cards |