Spaces:
Running
Running
| name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,few_cot,few_cot_self_con | |
| AquilaChat2-34B,36.63,36.63,44.83,44.83,46.65,46.65,, | |
| Baichuan-13B-Chat,12.47,11.67,16.5,19.52,24.55,22.54,26.36,28.77 | |
| Baichuan2-13B-Chat,17.1,19.1,18.7,22.9,25.9,26.5,20.9,24.5 | |
| ChatGLM2-6B,20.72,20.52,19.92,19.72,20.12,20.12,22.94,22.74 | |
| ChatGLM3-6B,20.92555332,20.92555332,25.15090543,25.15090543,24.74849095,24.74849095,29.1750503,29.1750503 | |
| Chinese-Alpaca-2-13B,23.14,23.14,28.97,28.97,16.3,16.3,14.29,14.29 | |
| Chinese-LLaMA-2-13B,13.88,13.88,20.52,20.52,16.9,16.9,23.34,23.34 | |
| DevOps-Model-14B-Chat,25.15,26.96,35.41,38.83,33.2,34.81,27.36,27.36 | |
| ERNIE-Bot-4.0,43.8,43.8,47.14,47.14,46.0,46.0,54.0,54.0 | |
| GPT-3.5-turbo,38.63,38.83,40.04,42.05,36.62,37.63,42.66,43.86 | |
| GPT-4,,,59.02,64.56,,,58.35,62.58 | |
| InternLM-7B,26.36,26.36,25.55,25.55,25.55,25.55,27.97,27.97 | |
| InternLM2-Chat-20B,,,59.21052632,59.21052632,,,, | |
| InternLM2-Chat-7B,27.16297787,27.16297787,28.16901408,28.16901408,29.97987928,29.97987928,30.18108652,30.18108652 | |
| LLaMA-2-13B,16.1,20.32,23.94,29.58,20.12,22.33,24.35,33.8 | |
| LLaMA-2-70B-Chat,19.72,19.72,27.97,27.97,26.56,26.56,32.6,32.6 | |
| LLaMA-2-7B,22.13,23.74,23.74,26.56,19.32,20.52,28.77,33.6 | |
| Mistral-7B,17.1,17.1,26.76,26.76,31.19,31.19,27.97,27.97 | |
| Qwen-14B-Chat,24.95,28.37,33.0,36.62,27.97,28.37,27.97,24.14 | |
| Qwen-72B-Chat,47.28,47.48,48.09,48.09,49.7,49.7,43.46,43.66 | |
| Qwen-7B-Chat,18.91,19.11,22.13,23.94,26.76,25.55,34.81,33.4 | |
| Yi-34B-Chat,47.08,48.69,47.08,46.28,58.15,58.35,56.94,58.95 | |
| Claude-3-Opus,48.31816996021653,48.31816996021653,,,,,, | |
| Deepseek-R1-Distill-Llama-8B,13.362518750407617,13.362518750407617,31.26345137937781,31.26345137937781,23.33528989760647,23.33528989760647,32.98441270462401,32.98441270462401 | |
| Deepseek-R1-Distill-Qwen-1.5B,15.083480075653819,15.083480075653819,18.153655514250307,18.153655514250307,16.92346572751582,16.92346572751582,24.784777929955,24.784777929955 | |
| Deepseek-R1-Distill-Qwen-14B,31.89199765212287,31.89199765212287,,,36.61628513663341,36.61628513663341,, | |
| Deepseek-R1-Distill-Qwen-32B,50.49240200873932,50.49240200873932,,,40.329681080023484,40.329681080023484,, | |
| Deepseek-R1-Distill-Qwen-7B,15.674525533163767,15.674525533163767,29.412867671036324,29.412867671036324,19.859942607447987,19.859942607447987,27.435107284940976,27.435107284940976 | |
| Gemma-2B,16.90141,16.90141,19.5171,19.5171,16.09658,16.09658,24.74849,24.74849 | |
| Gemma-7B,14.28571,14.28571,30.98592,30.98592,2.60223,2.60223,43.85965,43.85965 | |
| Meta-Llama-3-8B-Instruct,28.468825409248026,28.468825409248026,40.47805387073632,40.47805387073632,23.33528989760647,23.33528989760647,34.6197743429205,34.6197743429205 | |
| Qwen1.5-14B-Base,29.17505,29.17505,33.60161,33.60161,36.82093,36.82093,27.7666,27.7666 | |
| Qwen1.5-14B-Chat,32.79678,35.41247,39.43662,43.05835,32.39437,33.60161,36.82093,38.833 | |