Best Small AI Models

Small AI models (under 10B parameters) ranked by benchmark score. Lightweight models you can run locally.

106

Models

Providers

Open Source

$0.25

Median $/1M in

Top 3

Gemini 2.5 Pro Preview 05-06

Full Rankings

#	Model	Avg	$/1M in	Context
1	Gemini 2.5 Pro Preview 05-06🇺🇸 Google DeepMind	76.9	$1.25	1.0M
2	o4 Mini High🇺🇸 OpenAI	72.0	$1.10	200K
3	MiniMax M2🇨🇳 minimaxOpen	69.5	$0.30	205K
4	phi-3-small 7.4B🇺🇸 MicrosoftOpen	67.4	N/A	0K
5	Grok 3 Mini Beta🇺🇸 xAI	64.8	$0.30	131K
6	Gemini 2.0 Flash Lite🇺🇸 Google DeepMind	64.2	$0.07	1.0M
7	Qwen3 4B Thinking 2507🇨🇳 AlibabaOpen	60.6	N/A	0K
8	o3 Mini High🇺🇸 OpenAI	60.4	$1.10	200K
9	GPT-5.1-Codex-Mini🇺🇸 OpenAI	60.4	$0.25	400K
10	DeepSeek V4.1 Flash🇨🇳 DeepSeek	59.7	$0.15	1.0M
11	Mixtral 8x7B Instruct🇫🇷 Mistral AIOpen	57.8	$0.54	33K
12	Gemini 3.7 Flash🇺🇸 Google DeepMind	57.6	$0.75	1.0M
13	Gemini 3.8 Flash🇺🇸 Google DeepMind	57.4	$0.75	1.0M
14	Gemini 3 Pro🇺🇸 Google DeepMind	56.1	N/A	0K
15	Gemini 3.5 Flash🇺🇸 Google DeepMind	54.8	$1.50	1.0M
16	Mixtral 8x7B🇫🇷 Mistral AIOpen	54.3	N/A	0K
17	phi-3-mini 3.8B🇺🇸 MicrosoftOpen	54.3	N/A	0K
18	Gemini 3.6 Flash🇺🇸 Google DeepMind	53.7	$0.75	1.0M
19	Gemini 2.0 Pro🇺🇸 Google DeepMind	53.7	N/A	0K
20	Grok-3 mini🇺🇸 xAI	53.6	N/A	0K
21	Qwen2.5-Coder-3B🇨🇳 Alibaba QwenOpen	52.2	N/A	0K
22	GPT-5 Mini🇺🇸 OpenAI	51.5	$0.25	400K
23	Gemini 2.5 Pro Preview 06-05🇺🇸 Google DeepMind	50.9	$1.25	1.0M
24	Gemini 2.5 Pro🇺🇸 Google DeepMind	50.8	$1.25	1.0M
25	DeepSeek-Coder-V2-Lite-Base🇨🇳 DeepSeekOpen	50.8	N/A	0K
26	Qwen2 7B Instruct🇨🇳 AlibabaOpen	50.5	N/A	0K
27	MiniMax M2.7🇨🇳 minimaxOpen	50.5	$0.21	205K
28	MiniMax M3🇨🇳 minimaxOpen	49.9	$0.30	1.0M
29	Gemini 3 Flash Preview🇺🇸 Google DeepMind	49.6	$0.50	1.0M
30	MiniMax M2.5🇨🇳 minimaxOpen	48.6	$0.27	205K
31	Gemini 2.5 Flash Lite🇺🇸 Google DeepMind	48.6	$0.10	1.0M
32	o4 Mini🇺🇸 OpenAI	48.6	$1.10	200K
33	Gemini 3.1 Pro Preview🇺🇸 Google DeepMind	48.2	$2.00	1.0M
34	Gemini 2.0 Flash🇺🇸 Google DeepMind	48.0	$0.10	1.0M
35	Gemini 2.0 Flash (Dec 2024)🇺🇸 Google DeepMind	47.6	N/A	0K
36	Qwen2 VL 7B Instruct🇨🇳 AlibabaOpen	47.3	N/A	0K
37	Qwen3 4B Instruct 2507🇨🇳 AlibabaOpen	47.2	N/A	0K
38	Gemini 1.5 Flash (May 2024)🇺🇸 Google DeepMind	45.7	N/A	0K
39	Qwen3 8B🇨🇳 Alibaba QwenOpen	45.3	$0.12	131K
40	Meta Llama 3 8B Instruct🇺🇸 MetaOpen	45.2	N/A	0K
41	Gemini 3.1 Flash Lite🇺🇸 Google DeepMind	44.5	$0.25	1.0M
42	Qwen2.5 Coder 7B Instruct🇨🇳 AlibabaOpen	44.4	N/A	0K
43	Qwen2.5 Coder 7B Instruct🇨🇳 Alibaba QwenOpen	44.4	$0.03	33K
44	Meta Llama 3 8B🇺🇸 MetaOpen	44.2	N/A	0K
45	GPT-4o-mini (2024-07-18)🇺🇸 OpenAI	43.2	$0.15	128K
46	DeepSeek R1 Distill Llama 8B🇨🇳 DeepSeekOpen	41.6	N/A	0K
47	Mistral 7B V0.1🇫🇷 Mistral AIOpen	41.6	N/A	0K
48	Gemini 1.5 Pro (Feb 2024)🇺🇸 Google DeepMind	41.3	N/A	0K
49	U Baichuan 2-7B Unknown	40.3	N/A	0K
50	Gemini 2.5 Flash🇺🇸 Google DeepMind	39.3	$0.30	1.0M
51	GPT-5 Nano🇺🇸 OpenAI	39.2	$0.05	400K
52	Qwen2.5 Coder 1.5B Instruct🇨🇳 AlibabaOpen	38.8	N/A	0K
53	Qwen3.5-9B🇨🇳 Alibaba QwenOpen	38.5	$0.10	262K
54	Gemini 1.5 Pro (May 2024)🇺🇸 Google DeepMind	38.4	N/A	0K
55	Gemini 2.0 Flash Thinking (Jan 2025)🇺🇸 Google DeepMind	37.7	N/A	0K
56	GPT-5.4 Mini🇺🇸 OpenAI	37.5	$0.75	400K
57	GPT-4.1 Mini🇺🇸 OpenAI	36.6	$0.40	1.0M
58	Gemma 2 2b It🇺🇸 Google DeepMindOpen	36.4	N/A	0K
59	Gemini 3.5 Flash Lite🇺🇸 Google DeepMind	36.3	$0.30	1.0M
60	Gemma 2 9B🇺🇸 Google DeepMindOpen	36.0	$0.03	8K
61	o1-mini🇺🇸 OpenAI	35.0	N/A	0K
62	U XGen-7B Unknown	33.9	N/A	0K
63	GPT-5.4 Nano🇺🇸 OpenAI	32.7	$0.20	400K
64	DeepSeek R1 Distill Qwen 7B🇨🇳 DeepSeekOpen	32.7	N/A	0K
65	o3 Mini🇺🇸 OpenAI	32.5	$1.10	200K
66	open_llama_7b🇺🇸 MetaOpen	32.0	N/A	0K
67	GPT-4.1 Nano🇺🇸 OpenAI	30.9	$0.10	1.0M
68	Llama 3 8B Instruct🇺🇸 MetaOpen	30.8	$0.14	8K
69	Phi 4 Mini Instruct🇺🇸 MicrosoftOpen	29.4	N/A	0K
70	Phi 4 Mini Instruct🇺🇸 MicrosoftOpen	29.4	$0.08	131K
71	GPT-4o-mini🇺🇸 OpenAI	29.2	$0.15	128K
72	U Yi 6B UnknownOpen	29.2	N/A	0K
73	Gemma 2B🇺🇸 Google DeepMindOpen	29.1	N/A	0K
74	Qwen-1_8B🇨🇳 Alibaba QwenOpen	28.7	N/A	0K
75	Phi 3.5 Mini Instruct🇺🇸 MicrosoftOpen	28.2	N/A	0K
76	Phi 3 Mini 4k Instruct🇺🇸 MicrosoftOpen	27.6	N/A	0K
77	Llama 2 7b Chat Hf🇺🇸 MetaOpen	27.3	N/A	0K
78	Qwen2.5 3B Instruct🇨🇳 Alibaba	27.2	N/A	0K
79	Qwen2.5 7B Instruct🇨🇳 Alibaba QwenOpen	24.6	$0.10	33K
80	Llama 3.2 3B Instruct🇺🇸 MetaOpen	24.2	$0.05	131K
81	Llama 3.1 8B Instruct🇺🇸 MetaOpen	24.2	$0.02	131K
82	U Baichuan1-7B Unknown	23.7	N/A	0K
83	Llama 2 7b Hf🇺🇸 MetaOpen	23.6	N/A	0K
84	CodeQwen1.5-7B🇨🇳 Alibaba QwenOpen	23.1	N/A	0K
85	Hermes 2 Pro - Llama-3 8B🇺🇸 nousresearchOpen	22.1	$0.14	8K
86	Qwen2.5 Coder 0.5B Instruct🇨🇳 AlibabaOpen	20.8	N/A	0K
87	Gemini 1.0 Pro🇺🇸 Google DeepMind	18.8	N/A	0K
88	Mistral 7B Instruct V0.2🇫🇷 Mistral AIOpen	18.5	N/A	0K
89	Qwen2.5 1.5B Instruct🇨🇳 AlibabaOpen	18.4	N/A	0K
90	U RedPajama-INCITE-7B-Base Unknown	18.0	N/A	0K
91	DeepSeek Coder 6.7B🇨🇳 DeepSeekOpen	16.7	N/A	0K
92	U Magistral Small 1.1 Unknown	16.5	N/A	0K
93	Qwen2 1.5B Instruct🇨🇳 AlibabaOpen	14.1	N/A	0K
94	U stablelm-tuned-alpha-7b Unknown	13.6	N/A	0K
95	Mistral 7B Instruct v0.1🇫🇷 Mistral AIOpen	12.8	$0.11	3K
96	L Vicuna 7b V1.5 LMSYSOpen	10.9	N/A	0K
97	Gemma 2 2b🇺🇸 Google DeepMindOpen	10.4	N/A	0K
98	DeepSeek R1 Distill Qwen 1.5B🇨🇳 DeepSeekOpen	10.4	N/A	0K
99	Qwen2.5 0.5B Instruct🇨🇳 AlibabaOpen	10.1	N/A	0K
100	Llama 3.2 1B Instruct🇺🇸 MetaOpen	9.4	$0.03	60K
101	Llama 3.2 3B Instruct (free)🇺🇸 MetaOpen	8.7	Free	131K
102	Qwen2 0.5B🇨🇳 AlibabaOpen	7.2	N/A	0K
103	Qwen2 0.5B Instruct🇨🇳 AlibabaOpen	6.6	N/A	0K
104	Gemma 3 4B🇺🇸 Google DeepMindOpen	5.8	$0.05	131K
105	DeepSeek Coder 1.3B🇨🇳 DeepSeekOpen	3.2	N/A	0K
106	T TinyLlama 1.1B Chat V1.0 TinyLlamaOpen	2.8	N/A	0K

About this category

Small AI models under 10 billion parameters, ranked by benchmark score. These lightweight models can run on consumer hardware and edge devices while delivering surprisingly strong performance.

Related categories

Best Open Source AI Models

Open-source AI models ranked by benchmark score. Compare Llama, Mistral, DeepSeek, Qwen, and other open-weight models.

AI Models Under $1/1M Tokens

Cheapest AI models ranked by score. All models with input pricing under $1 per million tokens, sorted by benchmark performance.

Best AI Models for Coding

AI models ranked by coding benchmarks. Compare HumanEval+, SWE-bench Verified, Aider Polyglot, and more across all providers.

Frequently asked questions

What are the best small AI models?

Small models under 10B parameters have improved dramatically. The leaderboard above ranks them by benchmark performance across coding, reasoning, and knowledge tasks.

Can small AI models run on my laptop?

Yes. Models under 10B parameters can run on modern laptops with 16GB+ RAM using tools like Ollama, llama.cpp, or LM Studio.

How do small models compare to large ones?

Small models trade some capability for speed and efficiency. The best small models now match or exceed what large models achieved just one year ago.

Back to all models