# Question Answering on ARC Challenge (ARC-c and Avg Metrics) Source: [Question Answering on ARC Challenge (ARC-c and Avg Metrics)]() Collection index: [llms.txt]() Data updated: 2026-06-18T06:51:59.511Z Evaluation of model performance on the ARC Challenge dataset for Question Answering, reporting the ARC-c score and the overall average performance. 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 Challenge | | Metric | ARC-c Score | | 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 - [ARC-c Score](): Higher is better; unit: PERCENT. - [Average Performance](): Higher is better; unit: PERCENT. ## Recorded results | Method | ARC-c Score | Result date | Report paper | | --- | --- | --- | --- | | OursQ | 47.61 | Not recorded | 6a337b68206542251d7c4f03 | | Baseline | 47.53 | Not recorded | 6a337b68206542251d7c4f03 | | Baseline | 46.93 | Not recorded | 6a337b68206542251d7c4f03 | | Wanda | 46.84 | Not recorded | 6a337b68206542251d7c4f03 | | MoNE | 46.67 | Not recorded | 6a337b68206542251d7c4f03 | | Wanda | 46.59 | Not recorded | 6a337b68206542251d7c4f03 | | EAC-MoE | 46.16 | Not recorded | 6a337b68206542251d7c4f03 | | EAC-MoE | 45.05 | Not recorded | 6a337b68206542251d7c4f03 | | MoNE | 44.86 | Not recorded | 6a337b68206542251d7c4f03 | | He et al. | 44.86 | Not recorded | 6a337b68206542251d7c4f03 | | Wanda | 44.54 | Not recorded | 6a337b68206542251d7c4f03 | | Wanda | 44.37 | Not recorded | 6a337b68206542251d7c4f03 | | He et al. | 44 | Not recorded | 6a337b68206542251d7c4f03 | | PuzzleMoE | 44 | Not recorded | 6a337b68206542251d7c4f03 | | OursQ | 43.77 | Not recorded | 6a337b68206542251d7c4f03 | | PuzzleMoE | 43 | Not recorded | 6a337b68206542251d7c4f03 | | Attribution-guided and Coverage-Maximized Expert-wise Pruning | 42.58 | Not recorded | 6a337b68206542251d7c4f03 | | MoE-I2 | 42.58 | Not recorded | 6a337b68206542251d7c4f03 | | Attribution-guided and Coverage-Maximized Expert-wise Pruning | 42.49 | Not recorded | 6a337b68206542251d7c4f03 | | C-Prune | 41.72 | Not recorded | 6a337b68206542251d7c4f03 | | MoNE | 37.2 | Not recorded | 6a337b68206542251d7c4f03 | | He et al. | 33.15 | Not recorded | 6a337b68206542251d7c4f03 | | Wanda | 31.4 | Not recorded | 6a337b68206542251d7c4f03 | | He et al. | 28.67 | Not recorded | 6a337b68206542251d7c4f03 | | C-Prune | 24.4 | Not recorded | 6a337b68206542251d7c4f03 | | MoNE | 22.7 | Not recorded | 6a337b68206542251d7c4f03 | | MoNE | 22.53 | Not recorded | 6a337b68206542251d7c4f03 | ### OursQ ARC-c Score: 47.61. Result ID: 6a3394f4fbc373592c303c8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25% Q4b","Storage":"6.00GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Baseline ARC-c Score: 47.53. Result ID: 6a3394f4fbc373592c303c70. [Reporting paper]() Recorded evaluation configuration: {"Type":"None","Storage":"32.7GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Baseline ARC-c Score: 46.93. Result ID: 6a3394f4fbc373592c303c7d. [Reporting paper]() Recorded evaluation configuration: {"Type":"None","Storage":"31.41GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Wanda ARC-c Score: 46.84. Result ID: 6a3394f4fbc373592c303c7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25%","Storage":"31.41GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### MoNE ARC-c Score: 46.67. Result ID: 6a3394f4fbc373592c303c81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25%","Storage":"24.00GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Wanda ARC-c Score: 46.59. Result ID: 6a3394f4fbc373592c303c80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25% Q4b","Storage":"7.70GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### EAC-MoE ARC-c Score: 46.16. Result ID: 6a3394f4fbc373592c303c77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P11% Q3.03b","Storage":"7.19GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### EAC-MoE ARC-c Score: 45.05. Result ID: 6a3394f4fbc373592c303c78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P38% Q3.03b","Storage":"4.47GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### MoNE ARC-c Score: 44.86. Result ID: 6a3394f4fbc373592c303c83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25% Q4b","Storage":"6.00GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### He et al. ARC-c Score: 44.86. Result ID: 6a3394f4fbc373592c303c85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25% Q4b","Storage":"6.00GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Wanda ARC-c Score: 44.54. Result ID: 6a3394f4fbc373592c303c71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25%","Storage":"32.7GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Wanda ARC-c Score: 44.37. Result ID: 6a3394f4fbc373592c303c72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P50%","Storage":"32.7GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### He et al. ARC-c Score: 44. Result ID: 6a3394f4fbc373592c303c76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25% Q4b","Storage":"7.70GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### PuzzleMoE ARC-c Score: 44. Result ID: 6a3394f4fbc373592c303c79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"M25%","Storage":"25.04GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### OursQ ARC-c Score: 43.77. Result ID: 6a3394f4fbc373592c303c7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25% Q4b","Storage":"6.26GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### PuzzleMoE ARC-c Score: 43. Result ID: 6a3394f4fbc373592c303c7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"M50%","Storage":"17.34GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Attribution-guided and Coverage-Maximized Expert-wise Pruning ARC-c Score: 42.58. Result ID: 6a3394f4fbc373592c303c7b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P50%","Storage":"17.34GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### MoE-I2 ARC-c Score: 42.58. Result ID: 6a3394f4fbc373592c303c88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"L53.98%","Storage":"15.39GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Attribution-guided and Coverage-Maximized Expert-wise Pruning ARC-c Score: 42.49. Result ID: 6a3394f4fbc373592c303c89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P50%","Storage":"16.57GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### C-Prune ARC-c Score: 41.72. Result ID: 6a3394f4fbc373592c303c87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25% Q4b","Storage":"6.00GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### MoNE ARC-c Score: 37.2. Result ID: 6a3394f4fbc373592c303c82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P50%","Storage":"16.57GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### He et al. ARC-c Score: 33.15. Result ID: 6a3394f4fbc373592c303c84. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P50%","Storage":"16.57GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Wanda ARC-c Score: 31.4. Result ID: 6a3394f4fbc373592c303c7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P50%","Storage":"31.41GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### He et al. ARC-c Score: 28.67. Result ID: 6a3394f4fbc373592c303c75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P50%","Storage":"17.34GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### C-Prune ARC-c Score: 24.4. Result ID: 6a3394f4fbc373592c303c86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P50%","Storage":"16.57GB","Model Family":"DeepSeek-V2-Lite","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### MoNE ARC-c Score: 22.7. Result ID: 6a3394f4fbc373592c303c73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P25%","Storage":"25.04GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### MoNE ARC-c Score: 22.53. Result ID: 6a3394f4fbc373592c303c74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"P50%","Storage":"17.34GB","Model Family":"Deepseek-MoE-16B","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.