# Natural Language Inference on ChaosNLI (test) Source: [Natural Language Inference on ChaosNLI (test)]() Collection index: [llms.txt]() Data updated: 2026-04-03T08:53:02.547Z Evaluation of Natural Language Inference performance on the test split of the ChaosNLI dataset, reporting Top-1 accuracy and specific difference metrics. 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) | ChaosNLI (test) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [Difference (A vs B)](): Higher is better; unit: SCALAR. - [Difference (A vs C)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Model C (vote-proportion target) | 50.5 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model C (vote-proportion target) | 50.3 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model A (projection target) | 50 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model A (projection target) | 50 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model B (antipignistic target) | 49.9 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model A (projection target) | 49.9 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model B (antipignistic target) | 49.6 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model C (vote-proportion target) | 49.5 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model A (projection target) | 49.3 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model B (antipignistic target) | 48.9 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model C (vote-proportion target) | 48.6 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model B (antipignistic target) | 48.5 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model A (projection target) | 48.3 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model C (vote-proportion target) | 47.7 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model A (projection target) | 46.8 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model A (projection target) | 46.7 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model A (projection target) | 46.5 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model C (vote-proportion target) | 46.1 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model C (vote-proportion target) | 45.6 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model C (vote-proportion target) | 45.4 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model B (antipignistic target) | 45 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model B (antipignistic target) | 45 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model A (projection target) | 44.9 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model B (antipignistic target) | 44.7 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model B (antipignistic target) | 44.7 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model C (vote-proportion target) | 43.2 | Not recorded | 69cf49b30636e5bf4afcdb23 | | Model B (antipignistic target) | 42.1 | Not recorded | 69cf49b30636e5bf4afcdb23 | ### Model C (vote-proportion target) Top-1 Accuracy: 50.5. Result ID: 69cf7fd147f34ce924b97da5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_full","Val section":"val\_full","Learning Rate":"0.005"}. This record does not assert independent reproduction. ### Model C (vote-proportion target) Top-1 Accuracy: 50.3. Result ID: 69cf7fd147f34ce924b97db7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_easy","Val section":"val\_full","Learning Rate":"0.2"}. This record does not assert independent reproduction. ### Model A (projection target) Top-1 Accuracy: 50. Result ID: 69cf7fd147f34ce924b97da3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_full","Val section":"val\_full","Learning Rate":"0.007"}. This record does not assert independent reproduction. ### Model A (projection target) Top-1 Accuracy: 50. Result ID: 69cf7fd147f34ce924b97da9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_full","Val section":"val\_S\_easy","Learning Rate":"0.03"}. This record does not assert independent reproduction. ### Model B (antipignistic target) Top-1 Accuracy: 49.9. Result ID: 69cf7fd147f34ce924b97daa. [Reporting paper]() Recorded evaluation configuration: {"Train section":"train\_full","Val section":"val\_S\_easy","Learning Rate":"0.007"}. This record does not assert independent reproduction. ### Model A (projection target) Top-1 Accuracy: 49.9. Result ID: 69cf7fd147f34ce924b97db5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_easy","Val section":"val\_full","Learning Rate":"0.005"}. This record does not assert independent reproduction. ### Model B (antipignistic target) Top-1 Accuracy: 49.6. Result ID: 69cf7fd147f34ce924b97da4. [Reporting paper]() Recorded evaluation configuration: {"Train section":"train\_full","Val section":"val\_full","Learning Rate":"0.007"}. This record does not assert independent reproduction. ### Model C (vote-proportion target) Top-1 Accuracy: 49.5. Result ID: 69cf7fd147f34ce924b97dab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_full","Val section":"val\_S\_easy","Learning Rate":"0.08"}. This record does not assert independent reproduction. ### Model A (projection target) Top-1 Accuracy: 49.3. Result ID: 69cf7fd147f34ce924b97dbb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_easy","Val section":"val\_S\_easy","Learning Rate":"0.2"}. This record does not assert independent reproduction. ### Model B (antipignistic target) Top-1 Accuracy: 48.9. Result ID: 69cf7fd147f34ce924b97dbc. [Reporting paper]() Recorded evaluation configuration: {"Train section":"train\_S\_easy","Val section":"val\_S\_easy","Learning Rate":"0.09"}. This record does not assert independent reproduction. ### Model C (vote-proportion target) Top-1 Accuracy: 48.6. Result ID: 69cf7fd147f34ce924b97dbd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_easy","Val section":"val\_S\_easy","Learning Rate":"0.3"}. This record does not assert independent reproduction. ### Model B (antipignistic target) Top-1 Accuracy: 48.5. Result ID: 69cf7fd147f34ce924b97db6. [Reporting paper]() Recorded evaluation configuration: {"Train section":"train\_S\_easy","Val section":"val\_full","Learning Rate":"0.1"}. This record does not assert independent reproduction. ### Model A (projection target) Top-1 Accuracy: 48.3. Result ID: 69cf7fd147f34ce924b97db8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_easy","Val section":"val\_S\_amb","Learning Rate":"0.08"}. This record does not assert independent reproduction. ### Model C (vote-proportion target) Top-1 Accuracy: 47.7. Result ID: 69cf7fd147f34ce924b97dba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_easy","Val section":"val\_S\_amb","Learning Rate":"0.3"}. This record does not assert independent reproduction. ### Model A (projection target) Top-1 Accuracy: 46.8. Result ID: 69cf7fd147f34ce924b97daf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_amb","Val section":"val\_S\_amb","Learning Rate":"0.009"}. This record does not assert independent reproduction. ### Model A (projection target) Top-1 Accuracy: 46.7. Result ID: 69cf7fd147f34ce924b97dac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_amb","Val section":"val\_full","Learning Rate":"0.009"}. This record does not assert independent reproduction. ### Model A (projection target) Top-1 Accuracy: 46.5. Result ID: 69cf7fd147f34ce924b97db2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_amb","Val section":"val\_S\_easy","Learning Rate":"0.01"}. This record does not assert independent reproduction. ### Model C (vote-proportion target) Top-1 Accuracy: 46.1. Result ID: 69cf7fd147f34ce924b97dae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_amb","Val section":"val\_full","Learning Rate":"0.003"}. This record does not assert independent reproduction. ### Model C (vote-proportion target) Top-1 Accuracy: 45.6. Result ID: 69cf7fd147f34ce924b97da8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_full","Val section":"val\_S\_amb","Learning Rate":"0.0001"}. This record does not assert independent reproduction. ### Model C (vote-proportion target) Top-1 Accuracy: 45.4. Result ID: 69cf7fd147f34ce924b97db4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_amb","Val section":"val\_S\_easy","Learning Rate":"0.5"}. This record does not assert independent reproduction. ### Model B (antipignistic target) Top-1 Accuracy: 45. Result ID: 69cf7fd147f34ce924b97dad. [Reporting paper]() Recorded evaluation configuration: {"Train section":"train\_S\_amb","Val section":"val\_full","Learning Rate":"0.6"}. This record does not assert independent reproduction. ### Model B (antipignistic target) Top-1 Accuracy: 45. Result ID: 69cf7fd147f34ce924b97db3. [Reporting paper]() Recorded evaluation configuration: {"Train section":"train\_S\_amb","Val section":"val\_S\_easy","Learning Rate":"0.8"}. This record does not assert independent reproduction. ### Model A (projection target) Top-1 Accuracy: 44.9. Result ID: 69cf7fd147f34ce924b97da6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_full","Val section":"val\_S\_amb","Learning Rate":"0.5"}. This record does not assert independent reproduction. ### Model B (antipignistic target) Top-1 Accuracy: 44.7. Result ID: 69cf7fd147f34ce924b97da7. [Reporting paper]() Recorded evaluation configuration: {"Train section":"train\_full","Val section":"val\_S\_amb","Learning Rate":"0.6"}. This record does not assert independent reproduction. ### Model B (antipignistic target) Top-1 Accuracy: 44.7. Result ID: 69cf7fd147f34ce924b97db9. [Reporting paper]() Recorded evaluation configuration: {"Train section":"train\_S\_easy","Val section":"val\_S\_amb","Learning Rate":"0.7"}. This record does not assert independent reproduction. ### Model C (vote-proportion target) Top-1 Accuracy: 43.2. Result ID: 69cf7fd147f34ce924b97db1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Train section":"train\_S\_amb","Val section":"val\_S\_amb","Learning Rate":"0.7"}. This record does not assert independent reproduction. ### Model B (antipignistic target) Top-1 Accuracy: 42.1. Result ID: 69cf7fd147f34ce924b97db0. [Reporting paper]() Recorded evaluation configuration: {"Train section":"train\_S\_amb","Val section":"val\_S\_amb","Learning Rate":"0.7"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.