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。
Top Model
scarlett-7b
Top Score
-
Model Count
100
Data version
-
Data source: HuggingFace
| Model | Type | Parameters (B) | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | Architecture |
|---|---|---|---|---|---|---|---|---|---|---|
| scarlett-7b | Fine Tuned Models | 70 | 49.09 | 57.17 | 80.27 | 36.11 | 48.52 | 72.14 | 0.3 | LlamaForCausalLM |
| Baichuan2-7B-Base-LLaMAfied |
Data is for reference only. Official sources are authoritative. Click model names to view DataLearner model profiles.
| Fine Tuned Models |
| 70 |
| 48.99 |
| 49.57 |
| 73.45 |
| 54.86 |
| 37.54 |
| 70.72 |
| 7.81 |
| LlamaForCausalLM |
| vicuna-mmlu-val-only-correct-mcq-7b-ep2 | Fine Tuned Models | 70 | 48.96 | 52.99 | 77.67 | 47.92 | 43.17 | 71.9 | 0.08 | LlamaForCausalLM |
| tora-code-34b-v1.0 | Chat Models | 340 | 48.95 | 50.43 | 75.54 | 46.78 | 39.66 | 68.19 | 13.12 | LlamaForCausalLM |
| HamSter-0.2 | Fine Tuned Models | 72.4 | 48.91 | 50.09 | 73.65 | 50.39 | 49.63 | 69.69 | 0.0 | MistralForCausalLM |
| MedicWizard-7B | Fine Tuned Models | 66.1 | 48.88 | 53.5 | 78.39 | 44.61 | 41.32 | 70.56 | 4.93 | Unknown |
| chinese-alpaca-2-7b | Fine Tuned Models | 67 | 48.85 | 49.57 | 72.62 | 46.5 | 48.63 | 70.01 | 5.76 | Unknown |
| vicuna-class-shishya-all-hal-7b-ep3 | Fine Tuned Models | 70 | 48.75 | 45.48 | 77.21 | 51.54 | 44.83 | 71.03 | 2.43 | LlamaForCausalLM |
| llemma_7b | Fine Tuned Models | 70 | 48.75 | 46.16 | 62.98 | 47.87 | 38.88 | 63.3 | 33.28 | LlamaForCausalLM |
| GOAT-7B-Community | Fine Tuned Models | 70 | 48.71 | 48.81 | 74.63 | 49.58 | 42.48 | 72.3 | 4.47 | LlamaForCausalLM |
| ELYZA-japanese-Llama-2-7b | Fine Tuned Models | 70 | 48.7 | 52.22 | 76.42 | 44.6 | 37.92 | 72.69 | 8.34 | LlamaForCausalLM |
| una-llama-7b | Fine Tuned Models | 67.4 | 48.64 | 53.67 | 80.07 | 37.37 | 38.01 | 72.93 | 9.78 | LlamaForCausalLM |
| canarim-7b | Fine Tuned Models | 70 | 48.63 | 51.96 | 77.52 | 40.92 | 40.03 | 71.43 | 9.93 | LlamaForCausalLM |
| Dans-CreepingSenseOfDoom | Fine Tuned Models | 128.5 | 48.58 | 53.33 | 78.9 | 48.09 | 37.84 | 73.32 | 0.0 | Unknown |
| airoboros-7b-gpt4-1.1 | Fine Tuned Models | 70 | 48.57 | 54.61 | 80.15 | 39.25 | 41.22 | 73.09 | 3.11 | LlamaForCausalLM |
| vicuna-class-shishya-13b-ep3 | Fine Tuned Models | 130 | 48.52 | 46.5 | 80.36 | 57.06 | 35.0 | 72.22 | 0.0 | LlamaForCausalLM |
| youri-7b-chat | Chat Models | 67.4 | 48.51 | 51.19 | 76.09 | 46.06 | 41.17 | 75.06 | 1.52 | LlamaForCausalLM |
| tora-7b-v1.0 | Chat Models | 70 | 48.5 | 52.47 | 78.68 | 45.9 | 37.9 | 73.56 | 2.5 | LlamaForCausalLM |
| Llama-2-7B-GPTQ | Pretrained Models | 90.5 | 48.48 | 52.05 | 77.59 | 43.99 | 39.32 | 72.93 | 5.0 | LlamaForCausalLM |
| WizardLM-13B-Uncensored | Fine Tuned Models | 128.5 | 48.48 | 50.94 | 76.64 | 43.96 | 46.73 | 70.56 | 2.05 | Unknown |
| yayi2-30b-llama | Pretrained Models | 304 | 48.46 | 35.67 | 53.37 | 70.6 | 49.08 | 63.14 | 18.88 | LlamaForCausalLM |
| medalpaca-7b | Fine Tuned Models | 70 | 48.45 | 54.1 | 80.42 | 41.47 | 40.46 | 71.19 | 3.03 | LlamaForCausalLM |
| vicuna-7B-chemical | Fine Tuned Models | 70 | 48.42 | 49.83 | 74.42 | 44.1 | 51.7 | 67.17 | 3.34 | LlamaForCausalLM |
| airoboros-7b-gpt4-1.4 | Fine Tuned Models | 70 | 48.4 | 53.92 | 80.33 | 38.61 | 41.05 | 72.77 | 3.71 | LlamaForCausalLM |
| airoboros-l2-7b-gpt4-2.0 | Fine Tuned Models | 70 | 48.38 | 52.9 | 78.53 | 45.09 | 39.45 | 71.11 | 3.18 | LlamaForCausalLM |
| pygmalion-instruct | Unkown Model Types | 67.4 | 48.37 | 52.56 | 77.65 | 35.94 | 42.13 | 72.06 | 9.86 | Unknown |
| Wizard-Vicuna-7B-Uncensored | Fine Tuned Models | 66.1 | 48.27 | 53.41 | 78.85 | 37.09 | 43.48 | 72.22 | 4.55 | Unknown |
| Wizard-Vicuna-7B-Uncensored-HF | Fine Tuned Models | 70 | 48.27 | 53.41 | 78.85 | 37.09 | 43.48 | 72.22 | 4.55 | LlamaForCausalLM |
| NexusRaven-V2-13B | Fine Tuned Models | 130 | 48.21 | 45.14 | 67.4 | 44.88 | 44.54 | 66.38 | 20.92 | LlamaForCausalLM |
| 3BigReasonCinder | Fine Tuned Models | 30.2 | 48.16 | 41.72 | 65.16 | 44.79 | 44.76 | 64.96 | 27.6 | LlamaForCausalLM |
| vicuna-7b-v1.5-lora-mctaco | Fine Tuned Models | 66.1 | 48.02 | 45.65 | 75.65 | 49.27 | 43.12 | 69.93 | 4.47 | Unknown |
| multimaster-7b | Fine Tuned Models | 72.4 | 48.01 | 41.04 | 75.0 | 46.93 | 44.98 | 68.35 | 11.75 | MistralForCausalLM |
| airoboros-l2-7b-gpt4-m2.0 | Fine Tuned Models | 70 | 47.95 | 50.51 | 76.87 | 45.35 | 41.34 | 69.53 | 4.09 | LlamaForCausalLM |
| tigerbot-7b-base | Unkown Model Types | 70 | 47.93 | 47.7 | 72.08 | 45.11 | 42.27 | 69.61 | 10.84 | LlamaForCausalLM |
| openllama-7b-icl | Pretrained Models | 70 | 47.93 | 47.95 | 77.04 | 44.37 | 37.06 | 70.17 | 10.99 | LlamaForCausalLM |
| llama-2-7b-chat-hf-phr_mental_health-2048 | Fine Tuned Models | 66.1 | 47.92 | 52.39 | 75.39 | 39.77 | 42.89 | 71.19 | 5.91 | Unknown |
| llama_7b_qlora_pds-eval | Fine Tuned Models | 70 | 47.9 | 53.92 | 78.13 | 32.98 | 45.6 | 72.61 | 4.17 | Unknown |
| Uncensored-Frank-7B | Fine Tuned Models | 70 | 47.9 | 54.27 | 76.52 | 37.5 | 43.86 | 70.24 | 5.0 | LlamaForCausalLM |
| vicuna-tutor-shishya-model-7b-ep3 | Fine Tuned Models | 70 | 47.9 | 43.86 | 76.63 | 51.24 | 43.53 | 71.82 | 0.3 | LlamaForCausalLM |
| vicuna-class-shishya-ac-hal-7b-ep3 | Fine Tuned Models | 70 | 47.89 | 44.62 | 76.98 | 50.96 | 43.03 | 71.74 | 0.0 | LlamaForCausalLM |
| ToRoLaMa-7b-v1.0 | Fine Tuned Models | 70 | 47.87 | 51.71 | 73.82 | 45.34 | 44.89 | 70.09 | 1.36 | LlamaForCausalLM |
| ALMA-7B-Ja-V2 | Fine Tuned Models | 70 | 47.85 | 52.39 | 77.92 | 44.72 | 38.66 | 73.4 | 0.0 | LlamaForCausalLM |
| mhm-7b-v1.3-DPO-1 | Chat Models | 72.4 | 47.77 | 49.57 | 68.1 | 45.76 | 45.88 | 62.04 | 15.24 | MistralForCausalLM |
| vigogne-7b-instruct | Fine Tuned Models | 70 | 47.76 | 51.96 | 78.11 | 38.43 | 42.47 | 72.85 | 2.73 | LlamaForCausalLM |
| airoboros-7b-gpt4 | Fine Tuned Models | 70 | 47.7 | 53.07 | 78.69 | 38.9 | 40.72 | 73.09 | 1.74 | LlamaForCausalLM |
| airoboros-7b-gpt4-fp16 | Fine Tuned Models | 70 | 47.7 | 53.07 | 78.67 | 38.88 | 40.73 | 73.09 | 1.74 | LlamaForCausalLM |
| phi-1_5 | Pretrained Models | 0 | 47.69 | 52.9 | 63.79 | 43.89 | 40.89 | 72.22 | 12.43 | PhiForCausalLM |
| phi-1_5 | Pretrained Models | 0 | 47.69 | 52.9 | 63.79 | 43.89 | 40.89 | 72.22 | 12.43 | PhiForCausalLM |
| DukunLM-7B-V1.0-Uncensored | Fine Tuned Models | 70 | 47.68 | 51.11 | 75.62 | 39.82 | 43.95 | 69.53 | 6.07 | LlamaForCausalLM |
| ELYZA-japanese-Llama-2-7b-fast | Fine Tuned Models | 70 | 47.67 | 51.88 | 75.46 | 44.34 | 36.45 | 71.59 | 6.29 | LlamaForCausalLM |
| orca_mini_v2_ger_7b | Fine Tuned Models | 70 | 47.65 | 49.83 | 75.5 | 39.1 | 45.74 | 71.59 | 4.17 | LlamaForCausalLM |
| openthaigpt-1.0.0-alpha-7b-chat-ckpt-hf | Chat Models | 70 | 47.65 | 50.85 | 74.89 | 40.02 | 47.23 | 69.06 | 3.87 | LlamaForCausalLM |
| vicuna-chinese-replication-v1.1 | Fine Tuned Models | 0 | 47.65 | 42.83 | 71.47 | 47.47 | 47.24 | 67.4 | 9.48 | LlamaForCausalLM |
| MiniMerlin-3B | Fine Tuned Models | 30.2 | 47.63 | 44.37 | 66.56 | 43.21 | 47.07 | 64.4 | 20.17 | LlamaForCausalLM |
| baize-healthcare-lora-7B | Chat Models | 70 | 47.62 | 54.1 | 77.32 | 37.09 | 39.96 | 72.85 | 4.4 | Unknown |
| llama_7b_qlora_cds | Fine Tuned Models | 70 | 47.43 | 52.47 | 77.76 | 32.38 | 46.14 | 71.74 | 4.09 | Unknown |
| effi-7b | Fine Tuned Models | 70 | 47.42 | 55.12 | 78.07 | 35.91 | 39.71 | 72.53 | 3.18 | LlamaForCausalLM |
| airoboros-7b-gpt4-1.2 | Fine Tuned Models | 70 | 47.42 | 52.13 | 78.14 | 38.64 | 41.79 | 71.67 | 2.12 | LlamaForCausalLM |
| orca_mini_v2_7b | Fine Tuned Models | 66.1 | 47.41 | 50.77 | 76.02 | 39.5 | 43.86 | 71.43 | 2.88 | Unknown |
| airoboros-7b | Fine Tuned Models | 70 | 47.4 | 53.07 | 77.65 | 37.23 | 43.39 | 70.96 | 2.12 | LlamaForCausalLM |
| vicuna-shishya-7b-ep3-v1 | Fine Tuned Models | 66.1 | 47.4 | 45.9 | 76.36 | 50.04 | 40.32 | 71.74 | 0.0 | Unknown |
| CAlign-alpaca-7b | Fine Tuned Models | 70 | 47.39 | 50.94 | 74.55 | 38.56 | 46.89 | 72.06 | 1.36 | LlamaForCausalLM |
| guanaco-7B-HF | Fine Tuned Models | 70 | 47.34 | 52.99 | 80.05 | 35.32 | 39.2 | 71.43 | 5.08 | LlamaForCausalLM |
| open_llama_13b | Pretrained Models | 130 | 47.26 | 51.19 | 75.23 | 43.75 | 38.08 | 72.06 | 3.26 | LlamaForCausalLM |
| gov-qna-ko-merged | Fine Tuned Models | 467 | 47.24 | 39.51 | 39.06 | 71.86 | 48.61 | 56.75 | 27.67 | Unknown |
| mixtral-ko-qna-merged | Chat Models | 467 | 47.24 | 39.51 | 39.06 | 71.86 | 48.61 | 56.75 | 27.67 | Unknown |
| Mixtral-8x7B-MoE-RP-Story | Fine Tuned Models | 467 | 47.23 | 51.54 | 70.0 | 43.04 | 41.53 | 67.32 | 9.93 | MixtralForCausalLM |
| Asclepius-Llama2-7B | Chat Models | 70 | 47.15 | 50.85 | 76.53 | 43.61 | 43.31 | 68.27 | 0.3 | LlamaForCausalLM |
| youri-7b | Fine Tuned Models | 70 | 47.11 | 49.06 | 74.89 | 42.22 | 36.03 | 71.82 | 8.64 | LlamaForCausalLM |
| openllama-7b-base | Pretrained Models | 70 | 47.09 | 46.16 | 76.4 | 42.82 | 36.65 | 70.88 | 9.63 | LlamaForCausalLM |
| LLaMA-2-7B-32K | Fine Tuned Models | 70 | 47.07 | 47.53 | 76.14 | 43.33 | 39.23 | 71.9 | 4.32 | LlamaForCausalLM |
| airoboros-gpt-3.5-turbo-100k-7b | Fine Tuned Models | 70 | 47.05 | 53.07 | 76.16 | 33.63 | 45.07 | 70.8 | 3.56 | LlamaForCausalLM |
| dolphin-llama2-7b | Fine Tuned Models | 66.1 | 46.94 | 46.59 | 67.52 | 48.37 | 49.72 | 63.77 | 5.69 | Unknown |
| WhiteRabbitNeo-33B-v1 | Fine Tuned Models | 330 | 46.93 | 44.37 | 60.22 | 40.56 | 41.68 | 61.01 | 33.74 | LlamaForCausalLM |
| airoboros-7b-gpt4-1.3 | Fine Tuned Models | 70 | 46.91 | 52.47 | 77.98 | 41.97 | 35.73 | 72.3 | 0.99 | LlamaForCausalLM |
| Llama-2-7b-WikiChat-fused | Fine Tuned Models | 67.4 | 46.81 | 50.68 | 75.0 | 39.69 | 46.36 | 69.06 | 0.08 | LlamaForCausalLM |
| llama_7b_lora | Fine Tuned Models | 70 | 46.77 | 54.86 | 79.1 | 33.63 | 34.74 | 72.77 | 5.53 | Unknown |
| baize-v2-7b | Fine Tuned Models | 70 | 46.72 | 48.98 | 75.06 | 39.6 | 41.39 | 71.11 | 4.17 | LlamaForCausalLM |
| speechless-codellama-dolphin-orca-platypus-13b | Fine Tuned Models | 130 | 46.7 | 44.8 | 68.6 | 44.03 | 46.28 | 66.93 | 9.55 | LlamaForCausalLM |
| speechless-codellama-platypus-13b | Fine Tuned Models | 130 | 46.68 | 46.16 | 68.88 | 44.55 | 44.98 | 66.14 | 9.4 | LlamaForCausalLM |
| dolphin-2.2-yi-34b-200k | Fine Tuned Models | 340 | 46.67 | 42.24 | 68.22 | 55.51 | 45.94 | 64.17 | 3.94 | LlamaForCausalLM |
| dolphin-2.2-yi-34b-200k | Chat Models | 340 | 46.67 | 42.15 | 68.18 | 55.47 | 45.93 | 64.56 | 3.71 | Unknown |
| gogpt2-7b | Fine Tuned Models | 70 | 46.65 | 46.76 | 71.53 | 42.85 | 47.85 | 68.67 | 2.27 | LlamaForCausalLM |
| OpenHathi-7B-Hi-v0.1-Base | Fine Tuned Models | 68.7 | 46.64 | 49.49 | 74.34 | 41.38 | 37.46 | 71.27 | 5.91 | LlamaForCausalLM |
| llama-2-7b-small-model-new | Fine Tuned Models | 67.4 | 46.62 | 45.22 | 72.35 | 46.23 | 42.46 | 63.93 | 9.55 | LlamaForCausalLM |
| llama_7b_qlora | Fine Tuned Models | 70 | 46.61 | 55.12 | 78.26 | 35.71 | 33.98 | 72.06 | 4.55 | Unknown |
| stablelm-3b-4e1t | Pretrained Models | 28 | 46.58 | 46.59 | 75.94 | 45.23 | 37.2 | 71.19 | 3.34 | StableLMEpochForCausalLM |
| gogpt2-13b | Fine Tuned Models | 130 | 46.55 | 48.38 | 71.78 | 44.5 | 44.73 | 67.88 | 2.05 | LlamaForCausalLM |
| llama7b_alpaca_1gpu_bf16 | Fine Tuned Models | 66.1 | 46.49 | 52.73 | 78.78 | 36.26 | 33.71 | 72.93 | 4.55 | Unknown |
| dolphin-2.2-yi-34b-200k | Fine Tuned Models | 340 | 46.47 | 42.06 | 68.13 | 55.35 | 45.93 | 64.25 | 3.11 | LlamaForCausalLM |
| gogpt-7b | Fine Tuned Models | 70 | 46.38 | 48.81 | 73.79 | 43.03 | 41.0 | 69.77 | 1.9 | LlamaForCausalLM |
| llama-7b | Unkown Model Types | 67.4 | 46.37 | 50.94 | 77.81 | 35.69 | 34.33 | 71.43 | 8.04 | LlamaForCausalLM |
| airoboros-7b-gpt4-1.4.1-qlora | Fine Tuned Models | 70 | 46.34 | 52.73 | 77.89 | 38.77 | 36.07 | 70.32 | 2.27 | LlamaForCausalLM |
| speechless-codellama-dolphin-orca-platypus-13b | Fine Tuned Models | 130 | 46.32 | 45.82 | 67.71 | 45.88 | 44.67 | 65.35 | 8.49 | LlamaForCausalLM |
| speechless-codellama-orca-13b | Fine Tuned Models | 130 | 46.28 | 46.33 | 67.71 | 47.19 | 46.66 | 63.77 | 5.99 | LlamaForCausalLM |
| open_llama_7b_v2_med_instruct | Fine Tuned Models | 70 | 46.24 | 46.5 | 76.91 | 42.32 | 40.33 | 69.3 | 2.05 | LlamaForCausalLM |
| firefly-llama2-7b-pretrain | Fine Tuned Models | 67 | 46.18 | 48.63 | 74.83 | 41.04 | 39.08 | 70.24 | 3.26 | Unknown |
| stablelm-base-alpha-7b-v2 | Pretrained Models | 68.9 | 46.18 | 47.35 | 77.08 | 45.1 | 36.46 | 68.51 | 2.58 | StableLMAlphaForCausalLM |
| carl-7b | Fine Tuned Models | 70 | 46.16 | 53.5 | 78.29 | 33.96 | 40.29 | 68.59 | 2.35 | LlamaForCausalLM |
| vicuna-class-shishya-7b-ep3 | Fine Tuned Models | 70 | 46.14 | 40.61 | 76.72 | 50.77 | 36.87 | 71.9 | 0.0 | LlamaForCausalLM |