Hugging Face's logo

internlm
/
internlm3-8b-instruct

Text Generation
Safetensors
internlm3
conversational
custom_code
Model card Files Community
17
haijunlv commited on
Commit
30021cd
·
verified ·
1 Parent(s): 469ae1b

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -18
README.md CHANGED
@@ -479,24 +479,24 @@ InternLM3支持通过长思维链求解复杂推理任务的深度思考模式
479
 
480
  我们使用开源评测工具 [OpenCompass](https://github.com/internLM/OpenCompass/) 从学科综合能力、语言能力、知识能力、推理能力、理解能力五大能力维度对InternLM开展全面评测，部分评测结果如下表所示，欢迎访问[ OpenCompass 榜单 ](https://rank.opencompass.org.cn)获取更多的评测结果。
481
 
482
- | | 评测集\模型 | InternLM3-8B-Instruct | Qwen2.5-7B-Instruct | Llama3.1-8B-Instruct | GPT-4o-mini(close source) |
483
- | ------------ | ------------------------------- | --------------------- | ------------------- | -------------------- | ------------------------- |
484
- | General | CMMLU(0-shot) | **83.1** | 75.8 | 53.9 | 66.0 |
485
- | | MMLU(0-shot) | 76.6 | **76.8** | 71.8 | 82.7 |
486
- | | MMLU-Pro(0-shot) | **57.6** | 56.2 | 48.1 | 64.1 |
487
- | Reasoning | GPQA-Diamond(0-shot) | **37.4** | 33.3 | 24.2 | 42.9 |
488
- | | DROP(0-shot) | **83.1** | 80.4 | 81.6 | 85.2 |
489
- | | HellaSwag(10-shot) | **91.2** | 85.3 | 76.7 | 89.5 |
490
- | | KOR-Bench(0-shot) | **56.4** | 44.6 | 47.7 | 58.2 |
491
- | MATH | MATH-500(0-shot) | **83.0*** | 72.4 | 48.4 | 74.0 |
492
- | | AIME2024(0-shot) | **20.0*** | 16.7 | 6.7 | 13.3 |
493
- | Coding | LiveCodeBench(2407-2409 Pass@1) | **17.8** | 16.8 | 12.9 | 21.8 |
494
- | | HumanEval(Pass@1) | 82.3 | **85.4** | 72.0 | 86.6 |
495
- | Instrunction | IFEval(Prompt-Strict) | **79.3** | 71.7 | 75.2 | 79.7 |
496
- | LongContext | RULER(4-128K Average) | 87.9 | 81.4 | **88.5** | 90.7 |
497
- | Chat | AlpacaEval 2.0(LC WinRate) | **51.1** | 30.3 | 25.0 | 50.7 |
498
- | | WildBench(Raw Score) | **33.1** | 23.3 | 1.5 | 40.3 |
499
- | | MT-Bench-101(Score 1-10) | **8.59** | 8.49 | 8.37 | 8.87 |
500
 
501
  - 表中标粗的数值表示在对比的开源模型中的最高值。
502
  - 以上评测结果基于 [OpenCompass](https://github.com/internLM/OpenCompass/) 获得(部分数据标注`*`代表使用深度思考模式进行评测)，具体测试细节可参见 [OpenCompass](https://github.com/internLM/OpenCompass/) 中提供的配置文件。
 
479
 
480
  我们使用开源评测工具 [OpenCompass](https://github.com/internLM/OpenCompass/) 从学科综合能力、语言能力、知识能力、推理能力、理解能力五大能力维度对InternLM开展全面评测，部分评测结果如下表所示，欢迎访问[ OpenCompass 榜单 ](https://rank.opencompass.org.cn)获取更多的评测结果。
481
 
482
+ | | 评测集\模型 | InternLM3-8B-Instruct | Qwen2.5-7B-Instruct | Llama3.1-8B-Instruct | GPT-4o-mini(闭源) |
483
+ | ------------ | ------------------------------- | --------------------- | ------------------- | -------------------- | ----------------- |
484
+ | General | CMMLU(0-shot) | **83.1** | 75.8 | 53.9 | 66.0 |
485
+ | | MMLU(0-shot) | 76.6 | **76.8** | 71.8 | 82.7 |
486
+ | | MMLU-Pro(0-shot) | **57.6** | 56.2 | 48.1 | 64.1 |
487
+ | Reasoning | GPQA-Diamond(0-shot) | **37.4** | 33.3 | 24.2 | 42.9 |
488
+ | | DROP(0-shot) | **83.1** | 80.4 | 81.6 | 85.2 |
489
+ | | HellaSwag(10-shot) | **91.2** | 85.3 | 76.7 | 89.5 |
490
+ | | KOR-Bench(0-shot) | **56.4** | 44.6 | 47.7 | 58.2 |
491
+ | MATH | MATH-500(0-shot) | **83.0*** | 72.4 | 48.4 | 74.0 |
492
+ | | AIME2024(0-shot) | **20.0*** | 16.7 | 6.7 | 13.3 |
493
+ | Coding | LiveCodeBench(2407-2409 Pass@1) | **17.8** | 16.8 | 12.9 | 21.8 |
494
+ | | HumanEval(Pass@1) | 82.3 | **85.4** | 72.0 | 86.6 |
495
+ | Instrunction | IFEval(Prompt-Strict) | **79.3** | 71.7 | 75.2 | 79.7 |
496
+ | LongContext | RULER(4-128K Average) | 87.9 | 81.4 | **88.5** | 90.7 |
497
+ | Chat | AlpacaEval 2.0(LC WinRate) | **51.1** | 30.3 | 25.0 | 50.7 |
498
+ | | WildBench(Raw Score) | **33.1** | 23.3 | 1.5 | 40.3 |
499
+ | | MT-Bench-101(Score 1-10) | **8.59** | 8.49 | 8.37 | 8.87 |
500
 
501
  - 表中标粗的数值表示在对比的开源模型中的最高值。
502
  - 以上评测结果基于 [OpenCompass](https://github.com/internLM/OpenCompass/) 获得(部分数据标注`*`代表使用深度思考模式进行评测)，具体测试细节可参见 [OpenCompass](https://github.com/internLM/OpenCompass/) 中提供的配置文件。