Common Sense Reasoning On Arc Easy
المقاييس
Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Accuracy |
|---|---|
| llama-open-and-efficient-foundation-language-1 | 74.8 |
| glam-efficient-scaling-of-language-models | 68.0 |
| language-models-are-few-shot-learners | 71.2 |
| designing-effective-sparse-expert-models | 95.2 |
| massive-language-models-can-be-accurately | 69.65 |
| mamba-linear-time-sequence-modeling-with | 69.7 |
| parameter-efficient-sparsity-crafting-from | 86.2 |
| designing-effective-sparse-expert-models | 75.4 |
| llama-open-and-efficient-foundation-language-1 | 72.8 |
| unifying-language-learning-paradigms | 32.2 |
| massive-language-models-can-be-accurately | 68.35 |
| pythia-a-suite-for-analyzing-large-language | 70.2 |
| stay-on-topic-with-classifier-free-guidance | 79.1 |
| mixtral-of-experts | 80.5 |
| stay-on-topic-with-classifier-free-guidance | 84.2 |
| llama-open-and-efficient-foundation-language-1 | 80.0 |
| mixlora-enhancing-large-language-models-fine | 83.5 |
| mixlora-enhancing-large-language-models-fine | 77.7 |
| mixture-of-subspaces-in-low-rank-adaptation | 90.5 |
| massive-language-models-can-be-accurately | 71.04 |
| galactica-a-large-language-model-for-science-1 | 83.8 |
| palm-2-technical-report-1 | 85.6 |
| finetuned-language-models-are-zero-shot | 80.7 |
| stay-on-topic-with-classifier-free-guidance | 83.2 |
| unifying-language-learning-paradigms | 69.8 |
| galactica-a-large-language-model-for-science-1 | 40.7 |
| mixtral-of-experts | 83.1 |
| galactica-a-large-language-model-for-science-1 | 68.8 |
| glam-efficient-scaling-of-language-models | 74.8 |
| galactica-a-large-language-model-for-science-1 | 37.4 |
| llama-open-and-efficient-foundation-language-1 | 78.9 |
| bloomberggpt-a-large-language-model-for | 70.79 |
| palm-2-technical-report-1 | 89.7 |
| unifying-language-learning-paradigms | 38.4 |
| bloomberggpt-a-large-language-model-for | 73.99 |
| language-models-are-few-shot-learners | 68.8 |
| textbooks-are-all-you-need-ii-phi-1-5 | 76.1 |
| palm-2-technical-report-1 | 88.0 |
| stay-on-topic-with-classifier-free-guidance | 58.9 |
| pythia-a-suite-for-analyzing-large-language | 71.5 |
| mistral-7b | 80.0 |
| bloomberggpt-a-large-language-model-for | 71.25 |
| massive-language-models-can-be-accurately | 67.08 |
| massive-language-models-can-be-accurately | 28.03 |
| mixlora-enhancing-large-language-models-fine | 86.5 |
| finetuned-language-models-are-zero-shot | 79.6 |
| bloomberggpt-a-large-language-model-for | 75.93 |