List your company

Chat on AlpacaEval

3,213Win RateFine-tuned
-128.1872739.23641,606.662,474.0836Oct 25, 2023Feb 19, 2024Jun 16, 2024Oct 12, 2024Feb 6, 2025Jun 4, 2025Sep 30, 2025

Evaluation results

MethodLinks
Fine-tunedCR=1, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.043,213
IMPARTCR=32, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.041,877
Fine-tunedCR=1, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.041,839
DARECR=32, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.041,776
LowRankCR=32, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.041,718
Fine-tunedCR=1, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.041,563
IMPARTCR=32, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.04988
LowRankCR=32, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.04845
IMPARTCR=32, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.04713
LowRankCR=32, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.04572
DARECR=32, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.04227
Xwin-LM v0.1Size=70B, Align=dPPO2023.1095.57
GPT-4Align=RLHF2023.1095.28
TeacherTeacher-Student Model Pair=Gemma2-9B-IT -> Gemma2-2B-IT, Judge=GPT4-Turbo2025.0994.6
Llama2-ChatSize=70B, Align=RLHF2023.1092.66
Claude 2Align=RLHF2023.1091.36
ZephyrSize=7B, Align=dDPO2023.1090.6
CSD (S, S)Teacher-Student Model Pair=Gemma2-9B-IT -> Gemma2-2B-IT, Judge=GPT4-Turbo2025.0990.05
CSD (T, S)Teacher-Student Model Pair=Gemma2-9B-IT -> Gemma2-2B-IT, Judge=GPT4-Turbo2025.0989.92
DistiLLM-2Teacher-Student Model Pair=Gemma2-9B-IT -> Gemma2-2B-IT, Judge=GPT4-Turbo2025.0989.91
DLD (S)Teacher-Student Model Pair=Gemma2-9B-IT -> Gemma2-2B-IT, Judge=GPT4-Turbo2025.0989.84
GPT-3.5-turboAlign=RLHF2023.1089.37
Vicuna v1.3Size=33B, Align=dSFT2023.1088.99
TeacherTeacher-Student Model Pair=Qwen2.5-7B-IT -> Qwen2.5-1.5B-IT, Judge=GPT4-Turbo2025.0988.69
Xwin-LM v0.1Size=7B, Align=dPPO2023.1087.83
GuanacoSize=65B, Align=SFT2023.1071.8
DPKDTeacher-Student Model Pair=Gemma2-9B-IT -> Gemma2-2B-IT, Judge=GPT4-Turbo2025.0971.18
BackboneCR=1, Backbone=LLaMA2-13B, Fine-tuned Model=LLaMA2-Chat-13B2025.0471
DistiLLM-2Teacher-Student Model Pair=Qwen2.5-7B-IT -> Qwen2.5-1.5B-IT, Judge=GPT4-Turbo2025.0970.42
CSD (T, S)Teacher-Student Model Pair=Qwen2.5-7B-IT -> Qwen2.5-1.5B-IT, Judge=GPT4-Turbo2025.0970.42
DLD (T)Teacher-Student Model Pair=Qwen2.5-7B-IT -> Qwen2.5-1.5B-IT, Judge=GPT4-Turbo2025.0969.8
CSD (S, S)Teacher-Student Model Pair=Qwen2.5-7B-IT -> Qwen2.5-1.5B-IT, Judge=GPT4-Turbo2025.0969.64
DLD (S)Teacher-Student Model Pair=Qwen2.5-7B-IT -> Qwen2.5-1.5B-IT, Judge=GPT4-Turbo2025.0967.67
Falcon-InstructSize=40B, Align=dSFT2023.1045.71
DARECR=32, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.0436
DLD (T)Teacher-Student Model Pair=Gemma2-9B-IT -> Gemma2-2B-IT, Judge=GPT4-Turbo2025.0931.24
BackboneCR=1, Backbone=LLaMA2-7B, Fine-tuned Model=LLaMA2-Chat-7B2025.0410
BackboneCR=1, Backbone=LLaMA3-8B, Fine-tuned Model=LLaMA3-Instruct-8B2025.048
DPKDTeacher-Student Model Pair=Qwen2.5-7B-IT -> Qwen2.5-1.5B-IT, Judge=GPT4-Turbo2025.090.32