SOTAVerified|Agents Browse Leaderboard About

Instruction Following

Instruction following is the basic task of the model. This task is dedicated to evaluating the ability of the large model to follow human instructions. It is hoped that the model can generate controllable and safe answers.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 1135 papers

Title	Date	Tasks	Status	Hype
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction	Feb 17, 2025	Instruction FollowingVoice Cloning	CodeCode Available	7
Large Language Diffusion Models	Feb 14, 2025	In-Context LearningInstruction Following	CodeCode Available	7
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback	Dec 20, 2024	AllInstruction Following	CodeCode Available	7
Qwen2-Audio Technical Report	Jul 15, 2024	Instruction FollowingLanguage Modelling	CodeCode Available	7
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback	Jun 13, 2024	Instruction FollowingMath	CodeCode Available	7
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty	Jan 26, 2024	Code GenerationInstruction Following	CodeCode Available	7
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset	Sep 21, 2023	ChatbotDiversity	CodeCode Available	7
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models	Sep 21, 2023	4kGPU	CodeCode Available	6
Code Llama: Open Foundation Models for Code	Aug 24, 2023	16kCode Generation	CodeCode Available	6
L-Eval: Instituting Standardized Evaluation for Long Context Language Models	Jul 20, 2023	Instruction Following	CodeCode Available	6

Show:10 25 50

← PrevPage 2 of 114Next →

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	AutoIF (Llama3 70B)	Inst-level loose-accuracy	90.4	—	Unverified
2	AutoIF (Qwen2 72B)	Inst-level loose-accuracy	88	—	Unverified
3	GPT-4	Inst-level loose-accuracy	85.37	—	Unverified
4	PaLM 2 S	Inst-level loose-accuracy	59.11	—	Unverified