# Science Question Answering on ARC Challenge (Accuracy and Exit Position) Source: [Science Question Answering on ARC Challenge (Accuracy and Exit Position)]() Collection index: [llms.txt]() Data updated: 2026-04-21T13:26:35.532Z Evaluation of model performance on the ARC Challenge dataset for Science Question Answering, measured by Accuracy and Exit Position. 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 | Science Question Answering | | Dataset (including any stated split) | ARC Challenge | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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: PERCENT. - [Exit Position](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Ministral3 8B | 62.3 | Not recorded | 69e705277d0172140ec7f309 | | River-LLM | 62.2 | Not recorded | 69e705277d0172140ec7f309 | | River-LLM | 62.2 | Not recorded | 69e705277d0172140ec7f309 | | Phi4-mini | 57.1 | Not recorded | 69e705277d0172140ec7f309 | | River-LLM | 54.4 | Not recorded | 69e705277d0172140ec7f309 | | River-LLM | 54 | Not recorded | 69e705277d0172140ec7f309 | ### Ministral3 8B Accuracy: 62.3. Result ID: 69e77ae847f34ce924cf62cf. [Reporting paper]() Recorded evaluation configuration: {"Model Architecture":"Ministral3 8B (34 layers)","Evaluation Protocol":"Backbone"}. This record does not assert independent reproduction. ### River-LLM Accuracy: 62.2. Result ID: 69e77ae847f34ce924cf62d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Architecture":"Ministral3 8B (34 layers)","Early-exit threshold (tau)":"0.8","Evaluation Protocol":"Adaptive"}. This record does not assert independent reproduction. ### River-LLM Accuracy: 62.2. Result ID: 69e77ae847f34ce924cf62d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Architecture":"Ministral3 8B (34 layers)","Early-exit threshold (tau)":"0.9","Evaluation Protocol":"Adaptive"}. This record does not assert independent reproduction. ### Phi4-mini Accuracy: 57.1. Result ID: 69e77ae847f34ce924cf62cc. [Reporting paper]() Recorded evaluation configuration: {"Model Architecture":"Phi4-mini (32 layers)","Evaluation Protocol":"Backbone"}. This record does not assert independent reproduction. ### River-LLM Accuracy: 54.4. Result ID: 69e77ae847f34ce924cf62ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Architecture":"Phi4-mini (32 layers)","Early-exit threshold (tau)":"0.9","Evaluation Protocol":"Adaptive"}. This record does not assert independent reproduction. ### River-LLM Accuracy: 54. Result ID: 69e77ae847f34ce924cf62cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Architecture":"Phi4-mini (32 layers)","Early-exit threshold (tau)":"0.8","Evaluation Protocol":"Adaptive"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.