Skip to content

Latest commit

 

History

History
42 lines (34 loc) · 3.42 KB

排行榜Markdown.md

File metadata and controls

42 lines (34 loc) · 3.42 KB
Raw

排行榜

<script type="text/javascript"> $.get("/get_rank_stat", function(data){ var st = JSON.parse(data); $("#view_stat_of_rank_page").html(""+"浏览数:" + st.num + "    " + st.mtime+""); }); </script>

语言大模型排行榜

Models T1 T2 T4 T5 T6 T9 T10 SUM
GPT-4 81.33 80.89 21.2/88.6 44.3/99.5 10.6/97.6 19.4/93.6 18.1/95.4 750.52
Qwen-14B-Chat 80.12 84.89 20.2/82.6 39.2/97.5 12.6/96.0 20.8/87.7 16.4/89.4 727.34
Yi-6B-Chat 79.16 87.78 14.8/85.6 39.5/97.8 7.5/98.0 17.3/85.4 11.4/92.7 717.00
Baichuan2-13B-Chat 69.04 77.11 22.9/83.8 35.9/97.3 9.0/97.3 18.8/93.0 13.8/93.9 711.72
Qwen-7B-Chat 71.81 82.22 17.7/79.7 39.5/97.2 12.7/96.9 19.9/83.4 16.5/84.9 702.44
ChatGLM3-6B 63.98 71.56 21.0/83.5 36.1/96.4 9.1/95.1 19.0/89.6 14.9/89.1 689.43
InternLM-Chat-20B 62.89 76.44 11.0/50.8 49.6/95.7 12.1/96.9 22.2/90.4 17.2/92.0 677.21
InternLM-Chat-7B 62.65 66.00 18.7/72.7 37.8/87.6 15.4/88.0 19.9/81.1 17.5/89.6 656.81
LLaMa2-Chinese-13B-Chat-ms 49.64 62.89 16.1/75.5 35.6/94.0 10.1/88.3 20.4/84.1 14.1/77.1 627.65

多模态大模型排行榜

Models T3 T4 T6 T7 T8 T9 SUM
Qwen-VL-Chat 54.47 9.3/75.1 15.3/86.7 7.4/70.5 20.6/85.9 14.4/64.5 504.15
InternLM-XComposer-7B 48.94 8.9/77.9 16.1/86.4 10.5/56.4 32.7/67.7 19.7/77.6 502.76
TransCore-M 46.81 8.0/79.3 11.6/82.1 7.2/60.8 13.2/80.3 19.1/77.6 486.01
LLaVa-v1.5-13B 48.94 10.3/67.4 14.0/79.3 6.5/54.4 15.9/67.6 18.3/77.9 460.51
Chinese-LLaVa-Baichuan 20.43 6.9/73.5 9.9/84.6 4.2/60.5 10.3/73.4 14.0/82.0 439.80
VisualGLM-6B 26.38 10.1/73.0 11.6/77.6 7.4/64.0 8.8/75.2 14.6/65.6 434.18
mPLUG-Owl2 40.43 11.6/64.0 14.8/71.1 8.8/48.3 22.7/60.8 14.9/70.4 427.66
Chinese-LLaVa-Cllama2 8.09 7.6/65.5 10.3/83.5 4.5/54.1 9.3/74.7 12.2/79.5 409.39