How is this ranking computed?

It is the same family composite as the leaderboard. Each benchmark is weighted by how much of its spread survives its own measurement error.

Best AI for coding

Ranked by the coding composite: SWE-bench Verified, Aider polyglot and MirrorCode. Full leaderboard.

Rank	Model	Lab	Composite	Evidence	Out $/M
1	Claude Fable 5.1	Anthropic	100th	10 bench · 2 src	$50.00
2	o3-pro	—	99th	1 bench · 1 src	$88.00
3	gemini-2.5-pro-preview-06-05	—	98th	1 bench · 1 src	—
4	Grok 4	xAI	98th	6 bench · 2 src	$15.00
5	gemini-2.5-pro-preview-06-05	—	97th	1 bench · 1 src	—
6	o3 (high) + gpt-4.1	—	96th	1 bench · 1 src	—
7	Claude Fable 5	Anthropic	95th	14 bench · 2 src	$50.00
8	Gemini 2.5 Pro Preview 05-06	—	95th	1 bench · 1 src	$10.00
9	GPT 5	OpenAI	94th	13 bench · 3 src	$10.00
10	Gemini 2.5 Pro Preview 03-25	—	93rd	1 bench · 1 src	$10.00
11	Doubao-Seed-Code	ByteDance	92nd	1 bench · 1 src	$1.12
12	GLM-5.2	Zhipu	92nd	10 bench · 2 src	$4.40
13	DeepSeek v4	DeepSeek	91st	7 bench · 1 src	—
14	DeepSeek R1	—	90th	1 bench · 1 src	—
15	Qwen3.7-Max	Alibaba	89th	10 bench · 2 src	$9.00
16	Claude Opus 4.6	Anthropic	88th	4 bench · 1 src	—
17	claude-opus-4-20250514	—	88th	1 bench · 1 src	—
18	Claude 4.5 Opus	Anthropic	87th	1 bench · 1 src	$25.00
19	Qwen3.6 Max Preview	Alibaba	86th	7 bench · 1 src	free
20	Kimi K2.6	Kimi	85th	12 bench · 2 src	$4.00
21	Claude Opus 4.5	Anthropic	85th	6 bench · 1 src	—
22	MiniMax M2.5	MiniMax	84th	1 bench · 1 src	$1.20
23	Gemini 3.1 Pro Preview	Google	83rd	1 bench · 1 src	$12.00
24	Gemini 3 Flash Preview	Google	82nd	10 bench · 2 src	$3.00
25	Claude 4.6 Opus	Anthropic	81st	1 bench · 1 src	$25.00
26	Gemini 3.5 Flash	Google	81st	14 bench · 3 src	$9.00
27	Claude Sonnet 4.6	Anthropic	80th	2 bench · 1 src	—
28	GPT-5.3 Codex	OpenAI	79th	1 bench · 1 src	$14.00
29	Claude Opus 4	Anthropic	78th	7 bench · 2 src	$75.00
30	GLM-5.1	Zhipu	78th	8 bench · 1 src	$4.40
31	Claude Opus 4.1	Anthropic	77th	10 bench · 1 src	$75.00
32	Gemini 3 Pro Preview	Google	76th	6 bench · 2 src	$9.60
33	GPT 5.2 Codex	OpenAI	75th	2 bench · 2 src	$14.00
34	GLM 5	Zhipu	74th	6 bench · 2 src	$3.2647
35	o3	OpenAI	74th	11 bench · 3 src	$8.00
36	GPT 5.2	OpenAI	73rd	12 bench · 3 src	$14.00
37	Kimi K2.5	Kimi	72nd	7 bench · 2 src	$1.90
38	Claude 4.5 Sonnet	Anthropic	71st	1 bench · 1 src	$15.00
39	DeepSeek-V3.2-Exp	DeepSeek	71st	7 bench · 3 src	$0.326
40	Claude Sonnet 4.5	Anthropic	70th	8 bench · 1 src	—
41	DeepSeek R1 + claude-3-5-sonnet-20241022	—	69th	1 bench · 1 src	—
42	Claude 4 Sonnet	Anthropic	68th	1 bench · 1 src	$15.00
43	Claude 4 Opus	Anthropic	67th	1 bench · 1 src	$75.00
44	Claude Opus 4.7	Anthropic	67th	13 bench · 2 src	$25.00
45	claude-3-7-sonnet-20250219	—	66th	1 bench · 1 src	—
46	GPT-6 Astra	OpenAI	65th	11 bench · 2 src	$50.00
47	Qwen3 235B A22B diff, no think, Alibaba API	—	64th	1 bench · 1 src	—
48	Claude Sonnet 4	Anthropic	64th	7 bench · 3 src	$15.00
49	o1-2024-12-17	OpenAI	63rd	9 bench · 3 src	$60.00
50	Claude 4.5 Haiku	Anthropic	62nd	1 bench · 1 src	$5.00
51	GPT 5.1	OpenAI	61st	8 bench · 2 src	$10.00
52	o4-mini	OpenAI	61st	12 bench · 3 src	$4.40
53	Claude 3.7 Sonnet	Anthropic	60th	7 bench · 3 src	$15.00
54	GPT 5.1 Codex	OpenAI	59th	1 bench · 1 src	$10.00
55	DeepSeek R1	DeepSeek	58th	4 bench · 2 src	$1.70
56	claude-sonnet-4-20250514	—	57th	1 bench · 1 src	—
57	Multiple	Anthropic	57th	1 bench · 1 src	—
58	gemini-2.5-flash-preview-05-20	—	56th	1 bench · 1 src	—
59	DeepSeek V3	—	55th	1 bench · 1 src	—
60	Kimi K2 Instruct	Kimi	54th	7 bench · 3 src	free
61	Quasar Alpha	—	54th	1 bench · 1 src	—
62	Claude 3.7 Sonnet w/ Review Heavy	Anthropic	53rd	1 bench · 1 src	—
63	swe-search	Anthropic	52nd	1 bench · 1 src	—
64	Grok 3 Beta	xAI	51st	6 bench · 2 src	—
65	Optimus Alpha	—	50th	1 bench · 1 src	—
66	MiniMax M2	MiniMax	50th	1 bench · 1 src	$1.53
67	GPT-5.4	OpenAI	49th	13 bench · 2 src	$15.00
68	GPT 5 mini	OpenAI	48th	11 bench · 2 src	$2.00
69	GPT-5.5	OpenAI	47th	16 bench · 2 src	$30.00
70	TTS	OpenAI	47th	1 bench · 1 src	—
71	Qwen3.6 Plus	Alibaba	46th	9 bench · 2 src	$3.00
72	DeepSeek Chat V3	—	45th	1 bench · 1 src	—
73	gemini-2.5-flash-preview-04-17	—	44th	1 bench · 1 src	—
74	Devstral Small	Mistral	43rd	1 bench · 1 src	—
75	Qwen3-Coder-30B-A3B-Instruct	Alibaba	43rd	1 bench · 1 src	$0.60
76	Claude 3.5 Sonnet	Anthropic	42nd	2 bench · 2 src	$15.00
77	Gemini 2.5 Pro	Google	41st	8 bench · 2 src	$10.00
78	Qwen3-Coder 480B/A35B Instruct	Alibaba	40th	1 bench · 1 src	$1.80
79	GLM 4.6	Zhipu	40th	3 bench · 2 src	$1.40
80	GPT-4.5	OpenAI	39th	4 bench · 2 src	$150.00
81	GLM 4.5	Zhipu	38th	3 bench · 2 src	$1.30
82	gemini-2.5-flash-preview-05-20	—	37th	1 bench · 1 src	—
83	O3 Mini	OpenAI	36th	12 bench · 3 src	$4.40
84	Devstral	Mistral	36th	1 bench · 1 src	—
85	Frogboss 32B 2510	Microsoft	35th	1 bench · 1 src	—
86	GPT 4.1	OpenAI	34th	10 bench · 3 src	$8.00
87	Grok 3 Mini Beta	—	33rd	1 bench · 1 src	—
88	Qwen3 32B	Alibaba	33rd	4 bench · 2 src	$0.55
89	gemini-exp-1206	—	32nd	1 bench · 1 src	—
90	chatgpt-4o-latest	—	31st	1 bench · 1 src	$14.00
91	TTS	Alibaba	30th	1 bench · 1 src	—
92	DevStral Small 2505	Mistral	30th	1 bench · 1 src	—
93	Gemini 2.0 Pro exp-02-05	—	29th	1 bench · 1 src	$7.956
94	Frogmini 14B 2510	Microsoft	28th	1 bench · 1 src	—
95	GPT-5.6 Sol	OpenAI	27th	12 bench · 2 src	$10.00
96	o1-mini	OpenAI	26th	5 bench · 2 src	$4.40
97	Amazon.nova Premier v1:0	Amazon	26th	1 bench · 1 src	—
98	DeepSWE-Preview	Agentica	25th	1 bench · 1 src	—
99	Llama3-SWE-RL-70B	Meta	24th	1 bench · 1 src	—
100	Claude 3.5 Haiku	Anthropic	23rd	2 bench · 2 src	$4.00
101	SWE-agent-LM-32B	Alibaba	23rd	1 bench · 1 src	—
102	gpt-oss-120b	OpenAI	22nd	6 bench · 3 src	$0.798
103	QwQ-32B + Qwen 2.5 Coder Instruct	—	21st	1 bench · 1 src	—
104	DevStral Small 2507	Mistral	20th	1 bench · 1 src	—
105	GPT 5 nano	OpenAI	19th	11 bench · 2 src	$0.40
106	qwen-max-2025-01-25	—	19th	1 bench · 1 src	$6.392
107	Gemini 3.1 Pro Preview	Google	18th	12 bench · 2 src	$12.00
108	QwQ 32B	Alibaba	17th	4 bench · 2 src	$0.861
109	GPT 4.1 mini	OpenAI	16th	10 bench · 3 src	$1.60
110	Gemini 2.0 Flash Thinking	Google	16th	6 bench · 3 src	$0.42
111	GPT 4o	OpenAI	15th	9 bench · 3 src	$10.00
112	gemini-2.0-flash-thinking-exp-01-21	—	14th	1 bench · 1 src	—
113	Qwen2.5	Alibaba	13th	1 bench · 1 src	—
114	DeepSeek Chat V2.5	—	12th	1 bench · 1 src	—
115	Gemini 2.5 Flash	Google	12th	2 bench · 2 src	$2.50
116	yi-lightning	—	11th	1 bench · 1 src	—
117	command-a-03-2025-quality	—	10th	1 bench · 1 src	—
118	Codestral 25.01	—	9th	1 bench · 1 src	—
119	Llama 4 Maverick Instruct	Meta	9th	6 bench · 3 src	$0.60
120	Qwen2.5 Coder 32B Instruct	Alibaba	8th	2 bench · 2 src	$1.00
121	openhands-lm-32b-v0.1	—	7th	1 bench · 1 src	—
122	GPT-4.1 nano	OpenAI	6th	6 bench · 2 src	$0.40
123	MCTS Refine 7B	—	5th	1 bench · 1 src	—
124	Gemma 3 27B	Google	5th	5 bench · 2 src	free
125	GPT-4o mini	OpenAI	4th	8 bench · 2 src	$0.60
126	GPT-4	OpenAI	3rd	1 bench · 1 src	—
127	Claude 3 Opus	Anthropic	2nd	6 bench · 2 src	$75.00
128	Llama 4 Scout Instruct	Meta	2nd	5 bench · 2 src	$0.46
129	Claude 2	Anthropic	1st	4 bench · 2 src	—
130	SWE-Llama 7B	Meta	0th	1 bench · 1 src	—

Common questions

What is the best ai for coding right now?: Ranked by the coding composite: SWE-bench Verified, Aider polyglot and MirrorCode.
How is this ranking computed?: It is the same family composite as the leaderboard. Each benchmark is weighted by how much of its spread survives its own measurement error.