# Fatal Error on OpenAgent Tier-4 Source: [Fatal Error on OpenAgent Tier-4]() Collection index: [llms.txt]() Data updated: 2026-07-02T09:37:28.200Z Evaluation of agent performance on the OpenAgent Tier-4 dataset, specifically measuring the rate of fatal errors encountered, reported via the RR metric. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Fatal Error | | Dataset (including any stated split) | OpenAgent Tier-4 | | Metric | RR (Fatal Error Rate) | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 15 of 15 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [RR (Fatal Error Rate)](): Lower is better; unit: PERCENT. ## Recorded results | Method | RR (Fatal Error Rate) | Result date | Report paper | | --- | --- | --- | --- | | SFT-400 | 0 | Not recorded | 6a45f097dc71372d7795a3c6 | | SFT-600 | 0.1 | Not recorded | 6a45f097dc71372d7795a3c6 | | SFT-800 | 0.2 | Not recorded | 6a45f097dc71372d7795a3c6 | | SFT-200 | 0.3 | Not recorded | 6a45f097dc71372d7795a3c6 | | PAFT (EFP only) | 1.7 | Not recorded | 6a45f097dc71372d7795a3c6 | | PAFT (SRP only) | 2.1 | Not recorded | 6a45f097dc71372d7795a3c6 | | Base | 12.2 | Not recorded | 6a45f097dc71372d7795a3c6 | | PAFT (alpha=0.2) | 90.4 | Not recorded | 6a45f097dc71372d7795a3c6 | | PAFT (alpha=0.4) | 96.4 | Not recorded | 6a45f097dc71372d7795a3c6 | | SFT-400 + PAFT | 97.8 | Not recorded | 6a45f097dc71372d7795a3c6 | | PAFT (SBP only) | 99.2 | Not recorded | 6a45f097dc71372d7795a3c6 | | SFT-200 + PAFT | 99.3 | Not recorded | 6a45f097dc71372d7795a3c6 | | SFT-600 + PAFT | 99.6 | Not recorded | 6a45f097dc71372d7795a3c6 | | SFT-800 + PAFT | 99.6 | Not recorded | 6a45f097dc71372d7795a3c6 | | PAFT (alpha=0.3 default) | 99.6 | Not recorded | 6a45f097dc71372d7795a3c6 | ### SFT-400 RR (Fatal Error Rate): 0. Result ID: 6a46315460b88bb339863688. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"400"}. This record does not assert independent reproduction. ### SFT-600 RR (Fatal Error Rate): 0.1. Result ID: 6a46315460b88bb33986368a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"600"}. This record does not assert independent reproduction. ### SFT-800 RR (Fatal Error Rate): 0.2. Result ID: 6a46315460b88bb33986368c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"800"}. This record does not assert independent reproduction. ### SFT-200 RR (Fatal Error Rate): 0.3. Result ID: 6a46315460b88bb339863686. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"200"}. This record does not assert independent reproduction. ### PAFT (EFP only) RR (Fatal Error Rate): 1.7. Result ID: 6a46315460b88bb339863691. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"800","perturbation\_ratio":"0.3","component":"EFP"}. This record does not assert independent reproduction. ### PAFT (SRP only) RR (Fatal Error Rate): 2.1. Result ID: 6a46315460b88bb339863693. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"800","perturbation\_ratio":"0.3","component":"SRP"}. This record does not assert independent reproduction. ### Base RR (Fatal Error Rate): 12.2. Result ID: 6a46315460b88bb339863685. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PAFT (alpha=0.2) RR (Fatal Error Rate): 90.4. Result ID: 6a46315460b88bb33986368e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"800","perturbation\_ratio":"0.2"}. This record does not assert independent reproduction. ### PAFT (alpha=0.4) RR (Fatal Error Rate): 96.4. Result ID: 6a46315460b88bb339863690. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"800","perturbation\_ratio":"0.4"}. This record does not assert independent reproduction. ### SFT-400 + PAFT RR (Fatal Error Rate): 97.8. Result ID: 6a46315460b88bb339863689. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"400","PAFT":"true"}. This record does not assert independent reproduction. ### PAFT (SBP only) RR (Fatal Error Rate): 99.2. Result ID: 6a46315460b88bb339863692. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"800","perturbation\_ratio":"0.3","component":"SBP"}. This record does not assert independent reproduction. ### SFT-200 + PAFT RR (Fatal Error Rate): 99.3. Result ID: 6a46315460b88bb339863687. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"200","PAFT":"true"}. This record does not assert independent reproduction. ### SFT-600 + PAFT RR (Fatal Error Rate): 99.6. Result ID: 6a46315460b88bb33986368b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"600","PAFT":"true"}. This record does not assert independent reproduction. ### SFT-800 + PAFT RR (Fatal Error Rate): 99.6. Result ID: 6a46315460b88bb33986368d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"800","PAFT":"true"}. This record does not assert independent reproduction. ### PAFT (alpha=0.3 default) RR (Fatal Error Rate): 99.6. Result ID: 6a46315460b88bb33986368f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_steps":"800","perturbation\_ratio":"0.3"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.