# Zero-shot Question Answering on Commonsense Reasoning Suite (PIQA, WinoGrande, HellaSwag, ARC) Source: [Zero-shot Question Answering on Commonsense Reasoning Suite (PIQA, WinoGrande, HellaSwag, ARC)]() Collection index: [llms.txt]() Data updated: 2026-04-16T06:53:04.057Z Evaluation of zero-shot Question Answering performance across a specific suite comprising PIQA, WinoGrande, HellaSwag, and ARC (Easy and Challenge splits). 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 | Zero-shot Question Answering | | Dataset (including any stated split) | Commonsense Reasoning Suite (PIQA, WinoGrande, HellaSwag, ARC) Zero-shot Llama-2-70B | | Metric | PIQA Accuracy (Zero-shot) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [PIQA Accuracy (Zero-shot)](): Higher is better; unit: PERCENT. - [WinoGrande Accuracy (Zero-shot)](): Higher is better; unit: PERCENT. - [HellaSwag Accuracy (Zero-shot)](): Higher is better; unit: PERCENT. - [ARC-Easy Accuracy (Zero-shot)](): Higher is better; unit: PERCENT. - [ARC-Challenge Accuracy (Zero-shot)](): Higher is better; unit: PERCENT. - [Average Accuracy (Zero-shot)](): Higher is better; unit: PERCENT. ## Recorded results | Method | PIQA Accuracy (Zero-shot) | Result date | Report paper | | --- | --- | --- | --- | | Dense | 82.7 | Not recorded | 68fa79cc1e209131cea7f6b5 | | TRSP-ℓ1 | 81.45 | Not recorded | 68fa79cc1e209131cea7f6b5 | | TRSP-ℓ2 | 81.35 | Not recorded | 68fa79cc1e209131cea7f6b5 | | LaCo | 80.33 | Not recorded | 68fa79cc1e209131cea7f6b5 | | ShortGPT | 80.15 | Not recorded | 68fa79cc1e209131cea7f6b5 | | Shortened LLaMA | 79.52 | Not recorded | 68fa79cc1e209131cea7f6b5 | | SLEB | 78.81 | Not recorded | 68fa79cc1e209131cea7f6b5 | ### Dense PIQA Accuracy (Zero-shot): 82.7. Result ID: 69e0863a47f34ce924c938b5. [Reporting paper]() Recorded evaluation configuration: {"Pruning Ratio":"0%"}. This record does not assert independent reproduction. ### TRSP-ℓ1 PIQA Accuracy (Zero-shot): 81.45. Result ID: 69e0863a47f34ce924c938bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pruning Ratio":"25%"}. This record does not assert independent reproduction. ### TRSP-ℓ2 PIQA Accuracy (Zero-shot): 81.35. Result ID: 69e0863a47f34ce924c938ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pruning Ratio":"25%"}. This record does not assert independent reproduction. ### LaCo PIQA Accuracy (Zero-shot): 80.33. Result ID: 69e0863a47f34ce924c938b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pruning Ratio":"25%"}. This record does not assert independent reproduction. ### ShortGPT PIQA Accuracy (Zero-shot): 80.15. Result ID: 69e0863a47f34ce924c938b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pruning Ratio":"25%"}. This record does not assert independent reproduction. ### Shortened LLaMA PIQA Accuracy (Zero-shot): 79.52. Result ID: 69e0863a47f34ce924c938b9. [Reporting paper]() Recorded evaluation configuration: {"Pruning Ratio":"25%"}. This record does not assert independent reproduction. ### SLEB PIQA Accuracy (Zero-shot): 78.81. Result ID: 69e0863a47f34ce924c938b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pruning Ratio":"25%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.