Best AI Models for Coding

Q: Which AI model is best for coding?

The top-ranked coding model changes frequently. Check the live leaderboard above for the current leader based on HumanEval+, SWE-bench Verified, and other coding benchmarks.

Q: What benchmarks measure coding ability?

Key coding benchmarks include HumanEval+ (function completion), SWE-bench Verified (real GitHub issues), Aider Polyglot (multi-language editing), and Terminal-bench (CLI tasks).

Q: Are open-source models competitive for coding?

Yes. Several open-source models score competitively on coding benchmarks, especially models from DeepSeek and Meta.

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

108

Models

Providers

Open Source

$1.00

Median $/1M in

Top 3

Claude Mythos Preview

🇺🇸 Anthropic

1.0MN/A/M in

81.814 benchmarks

Full Rankings

#	Model	Avg	aider poly	GSO-Bench	swe bench	swe bench	terminal b	$/1M in	Context
1	GPT-5.5🇺🇸 OpenAI	85.0	-	-	-	-	82.7	$5.00	400K
2	GPT-5 Chat🇺🇸 OpenAI	81.9	88.0	-	-	-	-	$1.25	128K
3	Claude Mythos Preview🇺🇸 Anthropic	81.8	-	-	93.9	-	82.0	N/A	1.0M
4	Gemini 2.5 Pro Preview 05-06🇺🇸 Google DeepMind	76.9	76.9	-	-	-	-	$1.25	1.0M
5	GPT-6 Astra🇺🇸 OpenAI	74.7	-	79.4	-	-	-	$10.00	1.1M
6	o4 Mini High🇺🇸 OpenAI	72.0	72.0	-	-	-	-	$1.10	200K
7	Grok 3 Beta🇺🇸 xAI	69.5	53.3	-	-	-	-	$3.00	131K
8	gpt-oss-120b (free)🇺🇸 OpenAIOpen	68.7	41.8	-	-	-	-	Free	131K
9	Claude Fable 5.1🇺🇸 Anthropic	68.2	-	88.2	-	-	-	$10.00	1.0M
10	Claude Fable 5🇺🇸 Anthropic	67.6	-	78.4	-	-	-	$10.00	1.0M
11	GPT-5.6 Sol🇺🇸 OpenAI	65.8	-	76.5	-	-	-	$2.00	1.1M
12	Grok 3 Mini Beta🇺🇸 xAI	64.8	49.3	-	-	-	-	$0.30	131K
13	Qwen3.7 Max🇨🇳 Alibaba QwenOpen	62.0	-	-	77.3	-	-	$1.48	1.0M
14	o3 Pro🇺🇸 OpenAI	61.3	84.9	-	-	-	-	$20.00	200K
15	o3 Mini High🇺🇸 OpenAI	60.4	60.4	-	-	-	-	$1.10	200K
16	R1 0528🇨🇳 DeepSeekOpen	57.9	71.4	-	-	-	-	$0.50	164K
17	Claude Sonnet 5🇺🇸 Anthropic	57.7	-	37.3	-	-	-	$2.00	1.0M
18	Claude Opus 4.8🇺🇸 Anthropic	56.4	-	47.1	-	-	-	$5.00	1.0M
19	GLM 5.2🇨🇳 z-aiOpen	56.3	-	-	78.7	-	-	$0.03	1.0M
20	Gemini 3 Pro🇺🇸 Google DeepMind	56.2	-	18.6	72.9	-	69.4	N/A	0K
21	DeepSeek V3🇨🇳 DeepSeekOpen	56.2	48.4	-	-	-	-	$0.26	164K
22	Kimi K2 0711🇨🇳 moonshotaiOpen	56.1	59.1	4.9	-	-	27.8	$0.57	131K
23	GPT-5.3-Codex🇺🇸 OpenAI	55.4	-	-	74.8	-	77.3	$1.75	400K
24	DeepSeek V3 0324🇨🇳 DeepSeekOpen	55.1	55.1	-	-	-	-	$0.29	164K
25	Gemini 3.5 Flash🇺🇸 Google DeepMind	54.9	-	-	79.3	-	-	$1.50	1.0M
26	GLM 5🇨🇳 z-aiOpen	54.7	-	-	72.1	-	52.4	$1.00	205K
27	GLM 5.1🇨🇳 z-aiOpen	54.6	-	-	74.2	-	-	$1.40	205K
28	Gemini 2.0 Pro🇺🇸 Google DeepMind	54.3	35.6	-	-	-	-	N/A	0K
29	DeepSeek V4 Pro🇨🇳 DeepSeekOpen	54.1	-	-	77.6	-	-	$0.96	1.0M
30	Grok 4🇺🇸 xAI	54.0	79.6	-	-	-	27.2	N/A	0K
31	Qwen3 235B A22B🇨🇳 Alibaba QwenOpen	53.7	59.6	-	-	-	-	$0.46	131K
32	Grok-3 mini🇺🇸 xAI	53.7	49.3	-	-	-	-	N/A	0K
33	Qwen3.6 Plus🇨🇳 Alibaba QwenOpen	53.6	-	-	57.9	-	-	$0.33	1.0M
34	Grok 4 Fast🇺🇸 xAI	53.3	-	-	-	-	-	N/A	0K
35	gpt-oss-20b🇺🇸 OpenAIOpen	53.2	-	-	-	-	3.4	$0.02	131K
36	GPT-5🇺🇸 OpenAI	53.2	88.0	6.9	73.5	65.0	49.6	$1.25	400K
37	Qwen2.5 Coder 32B Instruct🇨🇳 Alibaba QwenOpen	53.1	16.4	-	-	-	-	$0.66	33K
38	Kimi K2 Thinking🇨🇳 moonshotaiOpen	52.2	-	-	-	63.4	35.7	$0.60	262K
39	GPT-5.4🇺🇸 OpenAI	52.1	-	31.4	76.9	-	81.8	$2.50	1.1M
40	Qwen3 32B🇨🇳 Alibaba QwenOpen	51.7	40.0	-	-	-	-	$0.08	131K
41	GPT-5 Mini🇺🇸 OpenAI	51.5	-	-	64.7	59.8	34.8	$0.25	400K
42	o3🇺🇸 OpenAI	51.3	81.3	8.8	62.3	58.4	-	$2.00	200K
43	Claude Opus 4.7🇺🇸 Anthropic	51.2	-	44.1	83.5	-	80.2	$5.00	1.0M
44	Qwen3.6 Max Preview🇨🇳 Alibaba QwenOpen	51.0	-	-	76.7	-	-	$1.03	262K
45	Gemini 2.5 Pro🇺🇸 Google DeepMind	50.9	83.1	3.9	57.6	-	32.6	$1.25	1.0M
46	Gemini 2.5 Pro Preview 06-05🇺🇸 Google DeepMind	50.9	83.1	-	-	-	-	$1.25	1.0M
47	GLM 4.6🇨🇳 z-aiOpen	50.8	-	-	-	-	24.5	$0.43	205K
48	MiniMax M2.7🇨🇳 minimaxOpen	50.5	-	-	-	-	45.1	$0.30	205K
49	Gemini 3 Flash Preview🇺🇸 Google DeepMind	49.8	-	9.8	75.4	-	64.3	$0.50	1.0M
50	Grok 4.20🇺🇸 xAI	49.5	-	-	-	-	57.3	$1.25	2.0M
51	Kimi K2.5🇨🇳 moonshotaiOpen	49.5	-	-	73.8	-	43.2	$0.50	262K
52	gpt-oss-120b🇺🇸 OpenAIOpen	49.3	41.8	-	-	26.0	18.7	$0.04	131K
53	MiniMax M2.5🇨🇳 minimaxOpen	48.6	-	-	-	-	42.7	$0.27	205K
54	o4 Mini🇺🇸 OpenAI	48.6	72.0	3.6	-	45.0	-	$1.10	200K
55	DeepSeek V3.2 Exp🇨🇳 DeepSeekOpen	48.4	74.2	-	-	-	-	$0.27	164K
56	DeepSeek V3.2🇨🇳 DeepSeekOpen	48.3	74.2	-	-	-	39.5	$0.28	164K
57	Qwen3 235B A22B Instruct 2507🇨🇳 Alibaba QwenOpen	48.3	59.6	-	-	-	-	$0.09	262K
58	Claude Opus 4.6🇺🇸 Anthropic	48.3	-	33.3	78.7	-	79.8	$5.00	1.0M
59	Gemini 3.1 Pro Preview🇺🇸 Google DeepMind	48.2	-	22.6	75.6	-	80.2	$2.00	1.0M
60	Claude 3.7 Sonnet🇺🇸 Anthropic	48.2	64.9	3.8	61.0	52.8	-	N/A	0K
61	Gemini 2.0 Flash🇺🇸 Google DeepMind	48.0	38.2	-	-	-	-	$0.10	1.0M
62	Gemini 2.0 Flash (Dec 2024)🇺🇸 Google DeepMind	47.8	38.2	-	-	-	-	N/A	0K
63	GPT-5.1🇺🇸 OpenAI	47.5	-	13.7	68.0	66.0	47.6	$1.25	400K
64	GLM 4.7🇨🇳 z-aiOpen	46.7	-	-	-	-	33.4	$0.60	205K
65	GPT-5.2🇺🇸 OpenAI	46.1	-	27.4	73.8	71.8	64.9	$1.75	400K
66	Claude Opus 4🇺🇸 Anthropic	46.1	72.0	6.9	70.7	67.6	-	$15.00	200K
67	R1🇨🇳 DeepSeekOpen	45.6	56.9	-	-	-	-	$0.70	64K
68	Claude Sonnet 4🇺🇸 Anthropic	45.6	61.3	4.9	-	64.9	-	$3.00	200K
69	Grok 3🇺🇸 xAI	45.5	53.3	-	-	-	-	N/A	0K
70	Claude Sonnet 4.6🇺🇸 Anthropic	45.4	-	-	75.2	-	53.4	$3.00	1.0M
71	o1🇺🇸 OpenAI	45.2	61.7	-	-	-	-	$15.00	200K
72	GPT-4o-mini (2024-07-18)🇺🇸 OpenAI	43.2	3.6	-	-	-	-	$0.15	128K
73	Gemma 3 27B (free)🇺🇸 Google DeepMindOpen	42.2	4.9	-	-	-	-	Free	131K
74	Qwen3.6 35B A3B🇨🇳 Alibaba QwenOpen	42.2	-	-	-	-	24.6	$0.10	262K
75	o1-preview🇺🇸 OpenAI	42.0	-	-	-	-	-	N/A	0K
76	Qwen2.5-Max🇨🇳 Alibaba QwenOpen	41.4	21.8	-	-	-	-	N/A	0K
77	Gemini 1.5 Pro (Feb 2024)🇺🇸 Google DeepMind	41.3	-	-	-	-	-	N/A	0K
78	Claude Opus 4.5🇺🇸 Anthropic	40.8	-	26.5	76.7	74.4	63.1	$5.00	200K
79	GPT-4.1🇺🇸 OpenAI	39.5	52.4	-	48.5	39.6	-	$2.00	1.0M
80	Claude 3.5 Sonnet🇺🇸 Anthropic	39.4	51.6	4.6	-	-	-	N/A	0K
81	Gemini 2.5 Flash🇺🇸 Google DeepMind	39.3	47.1	-	-	-	17.1	$0.30	1.0M
82	GPT-5 Nano🇺🇸 OpenAI	39.1	-	-	-	34.8	21.8	$0.05	400K
83	Qwen3.5-9B🇨🇳 Alibaba QwenOpen	39.0	-	-	-	-	9.2	$0.08	262K
84	Gemini 1.5 Pro (May 2024)🇺🇸 Google DeepMind	38.5	-	-	-	-	-	N/A	0K
85	Kimi K2.6🇨🇳 moonshotaiOpen	38.3	-	-	76.7	-	-	$0.95	262K
86	Llama 3.1 405B🇺🇸 MetaOpen	38.0	-	-	-	-	-	N/A	0K
87	Gemini 2.0 Flash Thinking (Jan 2025)🇺🇸 Google DeepMind	38.0	18.2	-	-	-	-	N/A	0K
88	Claude Sonnet 4.5🇺🇸 Anthropic	37.9	-	14.7	71.3	70.6	46.5	$3.00	1.0M
89	GPT-4.1 Mini🇺🇸 OpenAI	36.7	32.4	-	-	23.9	-	$0.40	1.0M
90	Claude 3.5 Haiku🇺🇸 Anthropic	36.7	28.0	-	-	-	-	N/A	0K
91	Gemma 3 27B🇺🇸 Google DeepMindOpen	36.6	4.9	-	-	-	-	$0.08	131K
92	Claude Opus 4.1🇺🇸 Anthropic	36.3	-	-	73.3	-	38.0	$15.00	200K
93	GPT-4.5🇺🇸 OpenAI	36.1	44.9	-	-	-	-	N/A	0K
94	GPT-4o (2024-08-06)🇺🇸 OpenAI	35.6	23.1	-	-	-	-	$2.50	128K
95	o1-mini🇺🇸 OpenAI	35.2	32.9	-	-	-	-	N/A	0K
96	Claude Haiku 4.5🇺🇸 Anthropic	33.6	-	-	-	-	35.5	$1.00	200K
97	Llama 3 70B Instruct🇺🇸 MetaOpen	32.4	-	-	-	-	-	$0.51	8K
98	o3 Mini🇺🇸 OpenAI	32.4	60.4	1.3	-	-	-	$1.10	200K
99	GPT-4o (2024-11-20)🇺🇸 OpenAI	32.3	23.1	0.0	31.0	21.6	-	$2.50	128K
100	Llama 3-70B🇺🇸 MetaOpen	32.1	-	-	-	-	-	N/A	0K
101	QwQ 32B🇨🇳 Alibaba QwenOpen	31.1	20.9	-	-	-	-	$0.15	131K
102	GPT-4.1 Nano🇺🇸 OpenAI	29.3	8.9	-	-	-	-	$0.10	1.0M
103	GPT-4o-mini🇺🇸 OpenAI	29.3	3.6	-	-	-	-	$0.15	128K
104	Claude 3 Opus🇺🇸 Anthropic	28.1	-	-	-	-	-	N/A	0K
105	Llama 4 Maverick🇺🇸 MetaOpen	27.9	15.6	-	-	21.0	-	$0.19	524K
106	Claude 3 Haiku🇺🇸 Anthropic	25.8	-	-	-	-	-	$0.25	200K
107	Mixtral 8x22B Instruct🇫🇷 Mistral AIOpen	23.9	-	-	-	-	-	$2.00	66K
108	Llama 4 Scout🇺🇸 MetaOpen	19.5	-	-	-	9.1	-	$0.10	1.3M

90+ Gold 80-89 70-79 60-69 <60Scores in % unless noted. Avg = unweighted mean across tested benchmarks.

About this category

Models ranked by coding performance across HumanEval+, SWE-bench Verified, Aider Polyglot, and other code generation benchmarks. Scores reflect real-world software engineering tasks including bug fixing, code completion, and multi-file editing.

Related categories

Best AI Models for Reasoning

AI models ranked by reasoning benchmarks. Compare GPQA Diamond, ARC-AGI, BBH, and other reasoning tests across all providers.

Best AI Models for Math

AI models ranked by math benchmarks. Compare MATH-500, GSM8K, and competition-level math scores across all providers.

Flagship AI Models

The best AI model from each provider, ranked by benchmark score. Compare the flagships from OpenAI, Anthropic, Google, Meta, and more.

Frequently asked questions

Which AI model is best for coding?

The top-ranked coding model changes frequently. Check the live leaderboard above for the current leader based on HumanEval+, SWE-bench Verified, and other coding benchmarks.

What benchmarks measure coding ability?

Key coding benchmarks include HumanEval+ (function completion), SWE-bench Verified (real GitHub issues), Aider Polyglot (multi-language editing), and Terminal-bench (CLI tasks).

Are open-source models competitive for coding?

Yes. Several open-source models score competitively on coding benchmarks, especially models from DeepSeek and Meta.

Back to all models