# Natural Language Inference on MNLI HardCD (challenge) Source: [Natural Language Inference on MNLI HardCD (challenge)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:28:05.039Z Evaluation of Natural Language Inference performance on the MNLI HardCD challenge set, measured by metrics such as Accuracy. 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 | Natural Language Inference | | Dataset (including any stated split) | MNLI HardCD (challenge) | | Metric | Accuracy | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 - [Accuracy](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | LMinTemps | 0.803 | Not recorded | 68fa6b341e209131cea2cdc0 | | LMin | 0.8 | Not recorded | 68fa6b341e209131cea2cdc0 | | LMinDirichlet | 0.798 | Not recorded | 68fa6b341e209131cea2cdc0 | | PoETemps | 0.796 | Not recorded | 68fa6b341e209131cea2cdc0 | | DRiFtTemps | 0.796 | Not recorded | 68fa6b341e209131cea2cdc0 | | DRiFtDirichlet | 0.796 | Not recorded | 68fa6b341e209131cea2cdc0 | | DRiFt | 0.795 | Not recorded | 68fa6b341e209131cea2cdc0 | | PoE | 0.794 | Not recorded | 68fa6b341e209131cea2cdc0 | | PoEDirichlet | 0.794 | Not recorded | 68fa6b341e209131cea2cdc0 | | InvRDirichlet | 0.789 | Not recorded | 68fa6b341e209131cea2cdc0 | | InvRTemps | 0.786 | Not recorded | 68fa6b341e209131cea2cdc0 | | InvR | 0.784 | Not recorded | 68fa6b341e209131cea2cdc0 | | CE | 0.768 | Not recorded | 68fa6b341e209131cea2cdc0 | ### LMinTemps Accuracy: 0.803. Result ID: 698e7112ffc3901de09d9eda. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### LMin Accuracy: 0.8. Result ID: 698e7112ffc3901de09d9ed9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### LMinDirichlet Accuracy: 0.798. Result ID: 698e7112ffc3901de09d9edb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### PoETemps Accuracy: 0.796. Result ID: 698e7112ffc3901de09d9ed1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### DRiFtTemps Accuracy: 0.796. Result ID: 698e7112ffc3901de09d9ed4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### DRiFtDirichlet Accuracy: 0.796. Result ID: 698e7112ffc3901de09d9ed5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### DRiFt Accuracy: 0.795. Result ID: 698e7112ffc3901de09d9ed3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### PoE Accuracy: 0.794. Result ID: 698e7112ffc3901de09d9ed0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### PoEDirichlet Accuracy: 0.794. Result ID: 698e7112ffc3901de09d9ed2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### InvRDirichlet Accuracy: 0.789. Result ID: 698e7112ffc3901de09d9ed8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Dirichlet"}. This record does not assert independent reproduction. ### InvRTemps Accuracy: 0.786. Result ID: 698e7112ffc3901de09d9ed7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"Temperature Scaling"}. This record does not assert independent reproduction. ### InvR Accuracy: 0.784. Result ID: 698e7112ffc3901de09d9ed6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. ### CE Accuracy: 0.768. Result ID: 698e7112ffc3901de09d9ecf. [Reporting paper]() Recorded evaluation configuration: {"Calibrator":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.