Best AI Models for Instruction Following

AI models ranked by instruction-following accuracy using the IFEval benchmark.

Last updated: 5m ago

#1 Model

GPT-5.4

Score: 93.5

Average Score

86.6

Across all ranked models

Models Ranked

With benchmark data

Weights:IFEval (100%)

Top Best for Instructions Models by Weighted Score

Top 15 models by weighted score

LMMarketCap.com

#	Model	Provider	Score	IFEval
1	GPT-5.4OpenAI	OpenAI	93.5	93.5
2	GPT-5.2OpenAI	OpenAI	93	93
3	Claude Opus 4.6Anthropic	Anthropic	92.8	92.8
4	GPT-5.1OpenAI	OpenAI	92.5	92.5
5	Llama 3.3 70B InstructMeta	Meta	92.1	92.1
6	GPT-5OpenAI	OpenAI	92	92
7	o3OpenAI	OpenAI	92	92
8	Claude Opus 4.5Anthropic	Anthropic	91.5	91.5
9	Gemini 3 Flash PreviewGoogle	Google	91	91
10	Claude Sonnet 4.6Anthropic	Anthropic	91	91
11	Claude Sonnet 4Anthropic	Anthropic	90.8	90.8
12	Claude Opus 4Anthropic	Anthropic	90.5	90.5
13	Claude Sonnet 4.5Anthropic	Anthropic	90.2	90.2
14	o3 MiniOpenAI	OpenAI	90.2	90.2
15	o4 MiniOpenAI	OpenAI	90	90
16	DeepSeek V3 0324DeepSeek	DeepSeek	89	89
17	GPT-4.1OpenAI	OpenAI	88.2	88.2
18	Llama 4 MaverickMeta	Meta	88	88
19	Gemini 2.5 ProGoogle	Google	87.2	87.2
20	DeepSeek V3DeepSeek	DeepSeek	87.1	87.1
21	Mistral LargeMistral AI	Mistral AI	86.5	86.5
22	o1OpenAI	OpenAI	86.5	86.5
23	R1 0528DeepSeek	DeepSeek	85.5	85.5
24	Gemini 2.5 FlashGoogle	Google	85.5	85.5
25	GPT-4oOpenAI	OpenAI	84.3	84.3
26	Claude Haiku 4.5Anthropic	Anthropic	84	84
27	Llama 3.1 70B InstructMeta	Meta	83.6	83.6
28	R1DeepSeek	DeepSeek	83.3	83.3
29	GPT-4o-miniOpenAI	OpenAI	80.4	80.4
30	Phi 4Microsoft	Microsoft	80.1	80.1
31	Command R7B (12-2024)Cohere	Cohere	77.1	77.1
32	Qwen2.5 7B InstructAlibaba	Alibaba	75.9	75.9
33	Llama 3.1 8B InstructMeta	Meta	72.1	72.1
34	Llama 3.2 3B InstructMeta	Meta	68.5	68.5

How scores are calculated

Each model's score is a weighted average of its available benchmark results. When a model is missing some benchmarks, the weights are re-normalized across the benchmarks that are available. All scores are on a 0-100 scale. Data sourced from official model cards, published papers, and third-party evaluation platforms.

Other Specialty Leaderboards

Best for Coding Best for Math Best for Reasoning Best for Writing Best for Data Analysis Best for Roleplay Best for Multilingual

Frequently Asked Questions

Based on our benchmark analysis, GPT-5.4 by OpenAI is currently the #1 ranked model for instructions, with a weighted score of 93.5/100.

Models are ranked using a weighted average of IFEval benchmark scores. All scores are normalized to a 0-100 scale.

We currently rank 34 models that have relevant benchmark data for instructions tasks.