Best Small AI Models

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

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	$0.26	197K
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	MiniMax M2.7🇨🇳 minimaxOpen	63.5	$0.30	197K
8	phi-3-mini 3.8B🇺🇸 MicrosoftOpen	61.0	N/A	0K
9	Gemini 3.1 Pro Preview🇺🇸 Google DeepMind	60.6	$2.00	1.0M
10	Qwen3 4B Thinking 2507🇨🇳 AlibabaOpen	60.6	N/A	0K
11	Gemini 3 Pro🇺🇸 Google DeepMind	60.5	N/A	0K
12	GPT-5.1-Codex-Mini🇺🇸 OpenAI	60.4	$0.25	400K
13	o3 Mini High🇺🇸 OpenAI	60.4	$1.10	200K
14	Gemini 2.5 Flash Lite🇺🇸 Google DeepMind	59.1	$0.10	1.0M
15	Mixtral 8x7B Instruct🇫🇷 Mistral AIOpen	57.8	$0.54	33K
16	Qwen3 8B🇨🇳 Alibaba QwenOpen	56.5	$0.05	41K
17	Gemini 2.5 Pro🇺🇸 Google DeepMind	56.2	$1.25	1.0M
18	GPT-5 Mini🇺🇸 OpenAI	56.0	$0.25	400K
19	MiniMax M2.5🇨🇳 minimaxOpen	55.1	$0.12	197K
20	Gemini 2.0 Pro🇺🇸 Google DeepMind	53.7	N/A	0K
21	o4 Mini🇺🇸 OpenAI	53.2	$1.10	200K
22	Gemini 2.5 Pro Preview 06-05🇺🇸 Google DeepMind	50.9	$1.25	1.0M
23	Qwen2 7B Instruct🇨🇳 AlibabaOpen	50.5	N/A	0K
24	Gemini 3 Flash Preview🇺🇸 Google DeepMind	49.1	$0.50	1.0M
25	Gemini 2.0 Flash🇺🇸 Google DeepMind	48.0	$0.10	1.0M
26	Gemini 1.5 Flash (May 2024)🇺🇸 Google DeepMind	47.4	N/A	0K
27	Qwen2 VL 7B Instruct🇨🇳 AlibabaOpen	47.3	N/A	0K
28	Qwen3 4B Instruct 2507🇨🇳 AlibabaOpen	47.2	N/A	0K
29	Grok 3 Mini🇺🇸 xAI	46.6	$0.30	131K
30	GPT-5 Nano🇺🇸 OpenAI	45.3	$0.05	400K
31	Meta Llama 3 8B Instruct🇺🇸 MetaOpen	45.2	N/A	0K
32	GPT-4.1 Mini🇺🇸 OpenAI	44.5	$0.40	1.0M
33	Qwen2.5 Coder 7B Instruct🇨🇳 Alibaba QwenOpen	44.4	$0.03	33K
34	Meta Llama 3 8B🇺🇸 MetaOpen	44.2	N/A	0K
35	GPT-4o-mini (2024-07-18)🇺🇸 OpenAI	43.2	$0.15	128K
36	Mistral 7B V0.1🇫🇷 Mistral AIOpen	41.6	N/A	0K
37	Gemini 1.5 Pro (Feb 2024)🇺🇸 Google DeepMind	41.3	N/A	0K
38	U Baichuan 2-7B Unknown	40.3	N/A	0K
39	Gemini 2.5 Flash🇺🇸 Google DeepMind	40.0	$0.30	1.0M
40	GPT-4o-mini🇺🇸 OpenAI	39.6	$0.15	128K
41	Qwen2.5 Coder 1.5B Instruct🇨🇳 AlibabaOpen	38.8	N/A	0K
42	o3 Mini🇺🇸 OpenAI	38.4	$1.10	200K
43	Gemini 2.0 Flash Thinking (Jan 2025)🇺🇸 Google DeepMind	37.7	N/A	0K
44	GPT-5.4 Mini🇺🇸 OpenAI	37.0	$0.75	400K
45	Gemma 2 2b It🇺🇸 Google DeepMindOpen	36.4	N/A	0K
46	Gemma 2 9B🇺🇸 Google DeepMindOpen	36.0	$0.03	8K
47	GPT-4.1 Nano🇺🇸 OpenAI	35.2	$0.10	1.0M
48	Qwen2.5 7B Instruct🇨🇳 Alibaba QwenOpen	35.2	$0.04	33K
49	o1-mini🇺🇸 OpenAI	34.9	N/A	0K
50	U XGen-7B Unknown	33.9	N/A	0K
51	DeepSeek R1 Distill Llama 8B🇨🇳 DeepSeekOpen	33.6	N/A	0K
52	DeepSeek R1 Distill Qwen 7B🇨🇳 DeepSeekOpen	32.7	N/A	0K
53	GPT-5.4 Nano🇺🇸 OpenAI	32.4	$0.20	400K
54	U Yi 6B UnknownOpen	31.4	N/A	0K
55	Llama 3 8B Instruct🇺🇸 MetaOpen	30.8	$0.03	8K
56	Phi 4 Mini Instruct🇺🇸 MicrosoftOpen	29.4	N/A	0K
57	Gemma 2B🇺🇸 Google DeepMindOpen	29.1	N/A	0K
58	Phi 3.5 Mini Instruct🇺🇸 MicrosoftOpen	28.2	N/A	0K
59	Phi 3 Mini 4k Instruct🇺🇸 MicrosoftOpen	27.6	N/A	0K
60	Llama 3.1 8B Instruct🇺🇸 MetaOpen	27.4	$0.02	16K
61	Llama 2 7b Chat Hf🇺🇸 MetaOpen	27.3	N/A	0K
62	Qwen2.5 3B Instruct🇨🇳 Alibaba	27.2	N/A	0K
63	Llama 3.2 3B Instruct🇺🇸 MetaOpen	24.2	$0.05	80K
64	U Baichuan1-7B Unknown	23.7	N/A	0K
65	Llama 2 7b Hf🇺🇸 MetaOpen	23.6	N/A	0K
66	Hermes 2 Pro - Llama-3 8B🇺🇸 nousresearchOpen	22.1	$0.14	8K
67	Gemini 1.0 Pro🇺🇸 Google DeepMind	21.1	N/A	0K
68	Mistral 7B Instruct V0.2🇫🇷 Mistral AIOpen	18.5	N/A	0K
69	Qwen2.5 1.5B Instruct🇨🇳 AlibabaOpen	18.4	N/A	0K
70	DeepSeek Coder 6.7B🇨🇳 DeepSeekOpen	16.7	N/A	0K
71	U Magistral Small 1.1 Unknown	16.6	N/A	0K
72	Llama 3.2 1B Instruct🇺🇸 MetaOpen	14.5	$0.03	60K
73	Qwen2.5 Coder 0.5B Instruct🇨🇳 AlibabaOpen	14.3	N/A	0K
74	Qwen2 1.5B Instruct🇨🇳 AlibabaOpen	14.1	N/A	0K
75	Mistral 7B Instruct v0.1🇫🇷 Mistral AIOpen	12.8	$0.11	3K
76	L Vicuna 7b V1.5 LMSYSOpen	10.9	N/A	0K
77	DeepSeek R1 Distill Qwen 1.5B🇨🇳 DeepSeekOpen	10.4	N/A	0K
78	Gemma 2 2b🇺🇸 Google DeepMindOpen	10.4	N/A	0K
79	Qwen2.5 0.5B Instruct🇨🇳 AlibabaOpen	10.1	N/A	0K
80	Llama 3.2 3B Instruct (free)🇺🇸 MetaOpen	8.7	Free	131K
81	Qwen2 0.5B🇨🇳 AlibabaOpen	7.2	N/A	0K
82	Qwen2 0.5B Instruct🇨🇳 AlibabaOpen	6.6	N/A	0K
83	DeepSeek Coder 1.3B🇨🇳 DeepSeekOpen	3.2	N/A	0K
84	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