加载中...
加载中...
Open LLM Leaderboard是追踪大模型评测结果的排行榜，通过追踪大语言模型和ChatBot在不同评测任务上的表现来对模型进行排名和评估。
数据来源: HuggingFace
| 模型名称 | 模型类型 | 参数大小(亿) | 平均分 | ARC分数 | HellaSwag分数 | MMLU分数 | TruthfulQA分数 | Winogrande分数 | GSM8K分数 | 模型架构 |
|---|---|---|---|---|---|---|---|---|---|---|
| zarafusionex-1.2-l2-7b | Fine Tuned Models | 70 | 53.73 | 56.66 | 79.16 | 51.94 | 51.29 | 74.74 | 8.57 | LlamaForCausalLM |
| mistral-7b-sft-open-orca-flan-50k | Chat Models | 72.4 | 53.7 | 58.79 | 81.92 |
数据仅供参考，以官方来源为准。模型名称旁的链接可跳转到 DataLearner 模型详情页。
| 55.72 |
| 37.49 |
| 77.98 |
| 10.31 |
| MistralForCausalLM |
| llama-2-13b-huangyt_FINETUNE2_3w | Fine Tuned Models | 128.5 | 53.69 | 58.62 | 82.32 | 54.25 | 38.17 | 76.8 | 11.98 | Unknown |
| openbuddy-mixtral-8x7b-v16.2-32k | Fine Tuned Models | 467.4 | 53.69 | 34.39 | 81.72 | 71.33 | 56.65 | 77.82 | 0.23 | MixtralForCausalLM |
| Llama-2-13b-chat-dutch | Chat Models | 130.2 | 53.69 | 59.3 | 81.45 | 55.82 | 38.23 | 76.64 | 10.69 | LlamaForCausalLM |
| airoboros-13b-gpt4-1.1 | Fine Tuned Models | 130 | 53.68 | 59.04 | 83.05 | 49.41 | 46.62 | 75.77 | 8.19 | LlamaForCausalLM |
| bimoGPT-llama2-13b | Unkown Model Types | 130 | 53.68 | 58.79 | 82.08 | 55.6 | 37.82 | 76.48 | 11.3 | Unknown |
| airoboros-13b-gpt4 | Fine Tuned Models | 130 | 53.64 | 59.39 | 83.29 | 47.89 | 47.65 | 75.77 | 7.88 | LlamaForCausalLM |
| platypus2-22b-relora | Chat Models | 218.3 | 53.64 | 57.51 | 82.36 | 54.94 | 43.62 | 77.11 | 6.29 | Unknown |
| PuffedLIMA13bQLORA | Fine Tuned Models | 130 | 53.63 | 59.9 | 84.39 | 53.68 | 39.9 | 75.22 | 8.72 | Unknown |
| deacon-13b | Chat Models | 130.2 | 53.63 | 57.85 | 82.63 | 55.25 | 39.33 | 76.32 | 10.39 | LlamaForCausalLM |
| llama-2-13b-FINETUNE3_3.3w-r4-q_k_v_o | Fine Tuned Models | 130 | 53.62 | 59.04 | 81.15 | 53.0 | 40.16 | 76.48 | 11.9 | LlamaForCausalLM |
| tora-13b-v1.0 | Chat Models | 130 | 53.62 | 58.96 | 82.31 | 54.73 | 40.25 | 75.61 | 9.86 | LlamaForCausalLM |
| MistralInstructLongish | Chat Models | 72.4 | 53.62 | 60.75 | 81.86 | 60.49 | 40.55 | 76.56 | 1.52 | MistralForCausalLM |
| internlm2-base-7b-llama | Pretrained Models | 77.4 | 53.62 | 54.35 | 79.47 | 54.05 | 43.23 | 71.43 | 19.18 | LlamaForCausalLM |
| Python-Code-13B | Fine Tuned Models | 130 | 53.61 | 58.79 | 81.66 | 54.78 | 42.83 | 74.03 | 9.55 | LlamaForCausalLM |
| llama2-13b-ft-mc4_nl_cleaned_tiny | Fine Tuned Models | 130.2 | 53.6 | 59.3 | 82.04 | 54.67 | 38.03 | 77.27 | 10.31 | LlamaForCausalLM |
| WizardLM-1.0-Uncensored-CodeLlama-34b | Chat Models | 334.8 | 53.59 | 56.4 | 75.45 | 54.51 | 43.06 | 72.45 | 19.64 | Unknown |
| tulu-13B-fp16 | Fine Tuned Models | 130 | 53.58 | 53.92 | 80.66 | 53.19 | 43.84 | 75.61 | 14.25 | LlamaForCausalLM |
| TacoBeLLM | Fine Tuned Models | 130.2 | 53.56 | 58.53 | 81.9 | 56.97 | 46.06 | 76.64 | 1.29 | LlamaForCausalLM |
| dolphin-llama-13b | Fine Tuned Models | 128.5 | 53.56 | 55.55 | 77.11 | 52.16 | 52.23 | 69.93 | 14.4 | Unknown |
| guanaco-13B-HF | Fine Tuned Models | 130 | 53.54 | 57.85 | 83.84 | 48.28 | 46.73 | 75.85 | 8.72 | LlamaForCausalLM |
| llama-2-13b-Open_Platypus_and_ccp_2.6w | Fine Tuned Models | 130 | 53.52 | 58.96 | 82.51 | 56.12 | 40.07 | 76.64 | 6.82 | LlamaForCausalLM |
| code-millenials-34b | Chat Models | 337.4 | 53.51 | 49.83 | 75.09 | 49.28 | 45.37 | 69.06 | 32.45 | LlamaForCausalLM |
| MoECPM-Untrained-4x2b | Merged Models or MoE Models | 77.9 | 53.51 | 46.76 | 72.58 | 53.21 | 38.41 | 65.51 | 44.58 | MixtralForCausalLM |
| vigogne-13b-chat | Fine Tuned Models | 130 | 53.5 | 58.62 | 80.85 | 47.76 | 48.73 | 76.72 | 8.34 | LlamaForCausalLM |
| openbuddy-mistral-7b-v13 | Fine Tuned Models | 70 | 53.5 | 52.3 | 75.09 | 56.34 | 50.81 | 71.74 | 14.71 | MistralForCausalLM |
| orca_mini_v3_7b | Chat Models | 70 | 53.47 | 56.91 | 79.64 | 52.37 | 50.51 | 74.27 | 7.13 | LlamaForCausalLM |
| orca_mini_v3_7b | Fine Tuned Models | 66.1 | 53.47 | 56.91 | 79.64 | 52.37 | 50.51 | 74.27 | 7.13 | Unknown |
| tigerbot-13b-base | Pretrained Models | 130 | 53.42 | 53.84 | 77.05 | 53.57 | 44.06 | 74.98 | 17.06 | Unknown |
| zarafusionex-1.1-l2-7b | Fine Tuned Models | 70 | 53.41 | 56.14 | 79.34 | 52.1 | 50.66 | 74.43 | 7.81 | LlamaForCausalLM |
| QuantumLM | Unkown Model Types | 0 | 53.41 | 55.8 | 79.74 | 54.17 | 46.71 | 74.19 | 9.86 | LlamaForCausalLM |
| samantha-mistral-instruct-7b | Chat Models | 71.1 | 53.4 | 53.5 | 75.14 | 51.72 | 58.81 | 70.4 | 10.84 | Unknown |
| GiftedConvo13bLoraNoEcons | Chat Models | 130 | 53.35 | 59.39 | 83.19 | 55.15 | 40.56 | 74.03 | 7.81 | Unknown |
| airoboros-l2-13b-2.1 | Fine Tuned Models | 130 | 53.34 | 59.47 | 82.47 | 54.83 | 44.65 | 75.06 | 3.56 | LlamaForCausalLM |
| llama-2-13b-FINETUNE5_4w-r4-q_k_v_o | Fine Tuned Models | 130 | 53.32 | 58.36 | 81.1 | 54.53 | 37.02 | 76.64 | 12.28 | LlamaForCausalLM |
| vicuna-13b-v1.3.0-GPTQ | Unkown Model Types | 162.2 | 53.29 | 54.35 | 79.47 | 51.97 | 50.88 | 74.66 | 8.42 | LlamaForCausalLM |
| vicuna-13B-1.1-HF | Fine Tuned Models | 128.5 | 53.29 | 52.73 | 80.13 | 51.94 | 52.08 | 74.19 | 8.64 | Unknown |
| vicuna-13b-1.1 | Fine Tuned Models | 130 | 53.29 | 52.73 | 80.13 | 51.94 | 52.08 | 74.19 | 8.64 | LlamaForCausalLM |
| Vicuna-13B-CoT-fp16 | Fine Tuned Models | 130 | 53.28 | 52.73 | 80.14 | 51.9 | 52.08 | 74.19 | 8.64 | LlamaForCausalLM |
| Llama-2-13B-GPTQ | Fine Tuned Models | 162.3 | 53.26 | 59.13 | 81.48 | 54.45 | 37.07 | 76.16 | 11.3 | LlamaForCausalLM |
| finance-chat | Fine Tuned Models | 0 | 53.26 | 53.75 | 76.6 | 50.16 | 44.54 | 75.69 | 18.8 | LlamaForCausalLM |
| BeingWell_llama2_7b | Fine Tuned Models | 70 | 53.22 | 54.95 | 78.27 | 47.46 | 45.93 | 74.19 | 18.5 | LlamaForCausalLM |
| llama-2-13b-FINETUNE2_TEST_2.2w | Fine Tuned Models | 130 | 53.2 | 56.23 | 82.7 | 55.35 | 39.55 | 76.72 | 8.64 | LlamaForCausalLM |
| MetaMath-Llemma-7B | Fine Tuned Models | 70 | 53.19 | 46.5 | 61.69 | 47.66 | 39.61 | 62.75 | 60.96 | LlamaForCausalLM |
| llama-2-13b-FINETUNE4_3.8w-r4-q_k_v_o | Fine Tuned Models | 130 | 53.18 | 54.78 | 81.4 | 54.73 | 41.02 | 76.64 | 10.54 | LlamaForCausalLM |
| fusedyi | Fine Tuned Models | 109.1 | 53.18 | 55.03 | 76.6 | 63.43 | 49.29 | 72.69 | 2.05 | LlamaForCausalLM |
| zarafusionix-l2-7b | Fine Tuned Models | 70 | 53.18 | 55.55 | 79.4 | 51.21 | 51.05 | 74.66 | 7.2 | LlamaForCausalLM |
| WizardLM-13B-V1-1-SuperHOT-8K-fp16 | Fine Tuned Models | 130 | 53.16 | 58.62 | 81.07 | 48.32 | 54.19 | 76.01 | 0.76 | LlamaForCausalLM |
| Athena-Platypus2-13B-QLora-0.80-epoch | Chat Models | 130.2 | 53.16 | 56.66 | 80.56 | 55.43 | 53.62 | 72.61 | 0.08 | Unknown |
| Airboros2.1-Platypus2-13B-QLora-0.80-epoch | Chat Models | 130.2 | 53.15 | 58.96 | 82.46 | 54.62 | 47.71 | 75.14 | 0.0 | Unknown |
| Airoboros-L2-13B-2.1-GPTQ | Fine Tuned Models | 162.3 | 53.14 | 58.96 | 81.72 | 53.16 | 44.68 | 74.35 | 5.99 | LlamaForCausalLM |
| Llama-2-13b-hf-ds_wiki_1024_full_r_64_alpha_16 | Chat Models | 130 | 53.14 | 59.04 | 82.33 | 55.36 | 35.75 | 76.32 | 10.01 | Unknown |
| MLewd-L2-13B | Fine Tuned Models | 130 | 53.12 | 58.28 | 82.32 | 54.67 | 48.66 | 73.48 | 1.29 | LlamaForCausalLM |
| manticore-13b-chat-pyg-GPTQ | Unkown Model Types | 162.2 | 53.11 | 57.85 | 81.07 | 47.56 | 47.77 | 75.93 | 8.49 | LlamaForCausalLM |
| llama2_7b_mmlu | Fine Tuned Models | 70 | 53.1 | 56.14 | 79.13 | 60.04 | 40.95 | 74.43 | 7.88 | LlamaForCausalLM |
| LlongOrca-7B-16k | Chat Models | 70 | 53.02 | 57.51 | 79.44 | 49.35 | 49.84 | 74.51 | 7.51 | LlamaForCausalLM |
| airoboros-l2-13b-gpt4-1.4.1 | Fine Tuned Models | 130 | 53.02 | 59.13 | 82.78 | 55.62 | 40.27 | 73.32 | 6.97 | LlamaForCausalLM |
| Walter-Mistral-7B | Chat Models | 72.4 | 53.0 | 58.87 | 83.43 | 58.65 | 39.93 | 77.03 | 0.08 | MistralForCausalLM |
| medicine-chat | Fine Tuned Models | 0 | 52.99 | 53.75 | 76.11 | 49.98 | 43.46 | 75.69 | 18.95 | LlamaForCausalLM |
| Code-290k-13B | Fine Tuned Models | 130 | 52.96 | 56.06 | 81.55 | 51.99 | 37.65 | 72.69 | 17.82 | LlamaForCausalLM |
| digital-socrates-7b | Fine Tuned Models | 70 | 52.95 | 54.44 | 75.99 | 51.41 | 44.88 | 73.09 | 17.89 | LlamaForCausalLM |
| zaraxe-l2-7b | Fine Tuned Models | 70 | 52.95 | 57.17 | 79.34 | 51.0 | 49.11 | 73.48 | 7.58 | LlamaForCausalLM |
| baize-v2-13b | Fine Tuned Models | 130 | 52.94 | 56.91 | 79.29 | 49.72 | 47.88 | 74.9 | 8.95 | LlamaForCausalLM |
| Llama-2-7b-chat-hf-afr-100step-flan-v2 | Chat Models | 70 | 52.92 | 53.24 | 78.43 | 48.43 | 45.66 | 72.3 | 19.48 | LlamaForCausalLM |
| llama2-22b-chat-wizard-uncensored | Fine Tuned Models | 218.3 | 52.9 | 56.23 | 80.39 | 53.62 | 45.76 | 70.24 | 11.14 | LlamaForCausalLM |
| Llama-2-13b-ft-instruct-es | Chat Models | 130 | 52.89 | 59.39 | 81.51 | 54.31 | 37.81 | 75.77 | 8.57 | LlamaForCausalLM |
| law-chat | Fine Tuned Models | 0 | 52.88 | 53.41 | 76.16 | 50.24 | 43.53 | 75.45 | 18.5 | LlamaForCausalLM |
| Llama-2-7b-chat-hf-afr-100step-flan | Chat Models | 70 | 52.88 | 52.9 | 78.44 | 48.4 | 45.67 | 72.38 | 19.48 | LlamaForCausalLM |
| archangel_sft-kto_llama13b | Chat Models | 130.2 | 52.87 | 56.14 | 80.8 | 47.84 | 39.42 | 76.16 | 16.83 | LlamaForCausalLM |
| chimera-inst-chat-13b-hf | Unkown Model Types | 130 | 52.86 | 55.38 | 78.93 | 50.6 | 50.12 | 73.95 | 8.19 | LlamaForCausalLM |
| Telugu-Llama2-7B-v0-Instruct | Chat Models | 70 | 52.86 | 53.58 | 78.33 | 47.63 | 43.26 | 73.95 | 20.39 | LlamaForCausalLM |
| japanese-stablelm-instruct-gamma-7b | Chat Models | 72.4 | 52.82 | 50.68 | 78.68 | 54.82 | 39.77 | 73.72 | 19.26 | MistralForCausalLM |
| Llama2-13B-no_robots-alpaca-lora | Fine Tuned Models | 130 | 52.77 | 58.87 | 82.43 | 53.11 | 40.46 | 75.3 | 6.44 | LlamaForCausalLM |
| ypotryll-22b-epoch2-qlora | Chat Models | 220 | 52.75 | 59.22 | 80.66 | 54.52 | 40.42 | 76.32 | 5.38 | Unknown |
| orca_mini_v2_13b | Fine Tuned Models | 128.5 | 52.75 | 55.12 | 79.69 | 50.07 | 52.56 | 72.69 | 6.37 | Unknown |
| Llama-2-7b-chat-hf-afr-200step-flan-v2 | Chat Models | 70 | 52.75 | 52.65 | 78.04 | 48.51 | 45.42 | 72.93 | 18.95 | LlamaForCausalLM |
| EverythingLM-13b-V2-16k | Fine Tuned Models | 130 | 52.75 | 58.7 | 80.88 | 49.69 | 47.37 | 73.01 | 6.82 | LlamaForCausalLM |
| ELYZA-japanese-Llama-2-13b-fast-instruct | Fine Tuned Models | 130 | 52.72 | 57.51 | 81.82 | 54.52 | 43.82 | 75.93 | 2.73 | LlamaForCausalLM |
| Synthia-7B-v1.2 | Fine Tuned Models | 70 | 52.71 | 54.35 | 79.29 | 49.33 | 48.92 | 73.56 | 10.84 | LlamaForCausalLM |
| MetaMath-13B-V1.0 | Fine Tuned Models | 130 | 52.71 | 49.49 | 76.48 | 47.74 | 41.58 | 72.45 | 28.51 | LlamaForCausalLM |
| yehoon_llama2 | Chat Models | 0 | 52.71 | 54.78 | 78.98 | 51.29 | 49.17 | 74.74 | 7.28 | Unknown |
| Nous-Capybara-7B | Fine Tuned Models | 66.1 | 52.7 | 55.29 | 80.73 | 48.72 | 51.13 | 73.32 | 6.97 | Unknown |
| Tulpar-7b-v0 | Fine Tuned Models | 70 | 52.69 | 56.31 | 79.01 | 52.55 | 51.68 | 73.88 | 2.73 | LlamaForCausalLM |
| Capybara-7B | Fine Tuned Models | 66.1 | 52.69 | 55.2 | 80.76 | 48.8 | 51.07 | 73.4 | 6.9 | Unknown |
| CodeEngine | Fine Tuned Models | 0 | 52.68 | 58.36 | 82.27 | 54.18 | 45.18 | 74.59 | 1.52 | LlamaForCausalLM |
| openbuddy-mixtral-8x7b-v16.1-32k | Fine Tuned Models | 467.4 | 52.68 | 29.1 | 82.27 | 71.37 | 55.97 | 77.35 | 0.0 | MixtralForCausalLM |
| Mistral-Trismegistus-7B | Chat Models | 70 | 52.66 | 54.1 | 77.91 | 54.49 | 49.36 | 70.17 | 9.93 | MistralForCausalLM |
| airoboros-l2-13b-gpt4-m2.0 | Fine Tuned Models | 130 | 52.66 | 59.22 | 81.02 | 53.73 | 39.7 | 73.64 | 8.64 | LlamaForCausalLM |
| Llama-2-7b-chat-hf-afr-200step-flan | Chat Models | 70 | 52.62 | 52.47 | 78.02 | 48.42 | 45.47 | 72.69 | 18.65 | LlamaForCausalLM |
| openbuddy-mistral-7b-v13.1 | Fine Tuned Models | 70 | 52.62 | 52.56 | 75.73 | 56.68 | 50.44 | 71.59 | 8.72 | MistralForCausalLM |
| LIMA-13b-hf | Fine Tuned Models | 130 | 52.61 | 57.42 | 81.68 | 48.72 | 41.76 | 77.19 | 8.87 | LlamaForCausalLM |
| Chinese-Llama-2-7b | Fine Tuned Models | 70 | 52.59 | 52.99 | 75.64 | 50.74 | 48.94 | 72.77 | 14.48 | LlamaForCausalLM |
| japanese-stablelm-base-gamma-7b | Fine Tuned Models | 72.4 | 52.59 | 50.34 | 77.47 | 54.75 | 41.2 | 73.95 | 17.82 | MistralForCausalLM |
| Mistral-7B-SFT | Fine Tuned Models | 72.4 | 52.58 | 46.5 | 75.69 | 51.04 | 52.02 | 72.77 | 17.44 | MistralForCausalLM |
| speechless-codellama-dolphin-orca-platypus-34b | Fine Tuned Models | 340 | 52.53 | 52.47 | 74.13 | 53.47 | 47.14 | 73.24 | 14.71 | LlamaForCausalLM |
| speechless-codellama-34b-v1.0 | Fine Tuned Models | 340 | 52.53 | 52.47 | 74.13 | 53.47 | 47.14 | 73.24 | 14.71 | LlamaForCausalLM |
| Llama-2-7b-chat-hf-10-attention-sparsity | Chat Models | 67.4 | 52.52 | 52.9 | 78.18 | 48.1 | 45.4 | 71.43 | 19.11 | LlamaForCausalLM |
| speechless-codellama-34b-v2.0 | Fine Tuned Models | 340 | 52.51 | 54.35 | 75.65 | 54.67 | 45.21 | 73.56 | 11.6 | LlamaForCausalLM |
| airoboros-l2-13b-gpt4-2.0 | Fine Tuned Models | 130 | 52.49 | 59.04 | 82.82 | 54.71 | 36.47 | 74.19 | 7.73 | LlamaForCausalLM |