OpenCodePapers

instruction-following-on-mtbench

Natural Language UnderstandingInstruction Following
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeScore (1-10)ModelNameReleaseDate
Qwen2.5 Technical Report✓ Link9.35Qwen2.5-72B-Instruct2024-12-19
Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance✓ Link9.20Falcon-H1-34B-Instruct2025-07-30
Qwen2 Technical Report✓ Link9.12Qwen2-72B-Instruct2024-07-15
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model✓ Link8.97DeepSeek-V2 Chat (RL)2024-05-07
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone✓ Link8.91Phi-3-Medium2024-04-22
HyperCLOVA X THINK Technical Report✓ Link8.8313HyperCLOVA X SEED 14B Think2025-06-27
A Zeroth-Order Paradigm for LLM Preference Alignment8.79Gemma-2-9B-it SimPO + ComPO2026-09-16
Qwen2 Technical Report✓ Link8.55Qwen2-57B-A14B-Instruct2024-07-15
Aria: An Open Multimodal Native Mixture-of-Experts Model✓ Link8.53Aria2024-10-08
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools✓ Link8.35GLM-4-9B-Chat2024-06-18
Mixtral of Experts✓ Link8.30Mixtral 8x7B Instruct2024-01-08
Nemotron-4 340B Technical Report✓ Link8.22Nemotron-4-340B-Instruct2024-06-17
Pixtral 12B✓ Link7.68Pixtral 12B2024-10-09
The Zamba2 Suite: Technical Report✓ Link7.42Zamba2-7B-Instruct2024-11-22
LSRIF: Logic-Structured Reinforcement Learning for Instruction Following7.0Distill-Qwen-14B (LsrIF)2026-01-10
Mistral 7B✓ Link6.84Mistral 7B Instruct2023-10-10
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model✓ Link6.13SmolLM2 1.7B Instruct2025-02-04
BitNet b1.58 2B4T Technical Report✓ Link5.85BitNet b1.58 2B4T2025-04-16
Check out how to contribute new results. Then edit this file on GitLab or GitHub.