# Question Answering on ARC-C (avg.@8) Source: [Question Answering on ARC-C (avg.@8)]() Collection index: [llms.txt]() Data updated: 2026-04-14T08:24:26.437Z Evaluation of model performance on the ARC-C dataset for Question Answering, specifically measured using the 'avg.@8' 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 | Question Answering | | Dataset (including any stated split) | ARC-C | | Metric | Accuracy (ARC-C avg.@8) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 (ARC-C avg.@8)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (ARC-C avg.@8) | Result date | Report paper | | --- | --- | --- | --- | | Qwen2.5-7B-Instruct | 92.42 | Not recorded | 68fa7ae21e209131cea85a73 | | Qwen2.5-7B-Instruct | 92.29 | Not recorded | 68fa7ae21e209131cea85a73 | | Qwen2.5-7B-Instruct | 92.25 | Not recorded | 68fa7ae21e209131cea85a73 | | Qwen2.5-7B-Instruct | 92.22 | Not recorded | 68fa7ae21e209131cea85a73 | | Llama3.1-8B-Instruct | 90.92 | Not recorded | 68fa7ae21e209131cea85a73 | | Llama3.1-8B-Instruct | 89.11 | Not recorded | 68fa7ae21e209131cea85a73 | | Llama3.1-8B-Instruct | 88.57 | Not recorded | 68fa7ae21e209131cea85a73 | | Llama3.1-8B-Instruct | 87.73 | Not recorded | 68fa7ae21e209131cea85a73 | ### Qwen2.5-7B-Instruct Accuracy (ARC-C avg.@8): 92.42. Result ID: 69ddf9b647f34ce924c55bdc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Pipeline":"PSFT → GRPO"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Accuracy (ARC-C avg.@8): 92.29. Result ID: 69ddf9b647f34ce924c55bdb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Pipeline":"PSFT"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Accuracy (ARC-C avg.@8): 92.25. Result ID: 69ddf9b647f34ce924c55bda. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Pipeline":"SFT → GRPO"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Accuracy (ARC-C avg.@8): 92.22. Result ID: 69ddf9b647f34ce924c55bd9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Pipeline":"SFT"}. This record does not assert independent reproduction. ### Llama3.1-8B-Instruct Accuracy (ARC-C avg.@8): 90.92. Result ID: 69ddf9b647f34ce924c55be0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Pipeline":"PSFT → GRPO"}. This record does not assert independent reproduction. ### Llama3.1-8B-Instruct Accuracy (ARC-C avg.@8): 89.11. Result ID: 69ddf9b647f34ce924c55bdf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Pipeline":"PSFT"}. This record does not assert independent reproduction. ### Llama3.1-8B-Instruct Accuracy (ARC-C avg.@8): 88.57. Result ID: 69ddf9b647f34ce924c55bde. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Pipeline":"SFT → GRPO"}. This record does not assert independent reproduction. ### Llama3.1-8B-Instruct Accuracy (ARC-C avg.@8): 87.73. Result ID: 69ddf9b647f34ce924c55bdd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Pipeline":"SFT"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.