💻 Coding

AI model rankings by coding capability — LiveCodeBench, SciCode, Terminal-Bench.

Código aberto100/100 modelos

#			Acesso
1	Claude Fable 5.1 Anthropic	99.3	Testar agora
2	GPT-5.6 Sol OpenAI	94.8	Testar agora
3	Claude Opus 5 Anthropic	94.8	Testar agora
4	GPT-6 Astra OpenAI	94.6	Testar agora
5	Muse Spark 1.3 Meta	94.0	Testar agora
6	Grok 4.6 SpaceXAI	93.9	–
7	Gemini 3.8 Flash Google	93.8	Testar agora
8	Qwen3.8 Max Alibaba	93.7	Testar agora
9	Gemini 3.7 Flash Google	93.2	Testar agora
10	GPT-5.6 Terra OpenAI	93.1	Testar agora
11	Kimi K3 Kimi	92.7	Testar agora
12	Claude Fable 5 Anthropic	92.3	Testar agora
13	GLM-5.3 Z AI	91.9	Testar agora
14	Qwen3.8-Flash-Next Alibaba	90.3	Testar agora
15	Claude Opus 4.8 Anthropic	89.7	Testar agora
16	GPT-5.5 OpenAI	89.7	Testar agora
17	Muse Spark 1.2 Meta	88.9	Testar agora
18	Qwen3.8 2.4T A95B Alibaba	88.7	Testar agora
19	GLM 5.3 Flash Z AI	88.6	Testar agora
20	Grok 4.5 SpaceXAI	88.6	Testar agora
21	Claude Opus 4.7 Anthropic	88.2	Testar agora
22	GPT-5.6 Luna OpenAI	87.5	Testar agora
23	Claude Sonnet 5 Anthropic	87.5	Testar agora
24	Muse Spark 1.1 Meta	87.4	Testar agora
25	DeepSeek V4 Flash 0731 DeepSeek	85.6	Testar agora
26	DeepSeek V4 Pro 0813 DeepSeek	85.5	Testar agora
27	Gemini 3.6 Flash Google	85.5	Testar agora
28	Gemini 3.5 Flash Google	85.1	Testar agora
29	Qwen3.8 27B Alibaba	84.8	Testar agora
30	GPT-5.4 OpenAI	84.7	Testar agora
31	GLM-5.2 Z AI	84.3	Testar agora
32	Gemini 3.1 Pro Preview Google	82.0	Testar agora
33	DeepSeek V4 Flash Vision DeepSeek	81.7	Testar agora
34	Qwen3.7 Max Alibaba	80.8	Testar agora
35	Motif 3 Motif Technologies	79.9	–
36	K2 Horizon 375B A23B Institute of Foundation Models	78.2	–
37	Quasar 438B Multiverse Computing	77.5	–
38	Apodex 1.1 Apodex	77.4	–
39	Claude Sonnet 4.6 Anthropic	75.9	Testar agora
40	Kimi K2.7 Code Kimi	75.8	Testar agora
41	Kimi K2.6 Kimi	75.8	Testar agora
42	Hy3 Tencent	74.2	–
43	MiMo-V2.5-Pro Xiaomi	74.2	–
44	Nex-N2-Pro Nex AGI	73.9	–
45	Ling-3.0-flash-VL InclusionAI	73.7	–
46	DeepSeek V4 Pro 0424 DeepSeek	73.4	Testar agora
47	MiniMax-M3 MiniMax	73.3	Testar agora
48	KAT Coder Pro V2 KwaiKAT	72.9	–
49	Muse Spark Meta	72.2	Testar agora
50	Ling-3.0-flash-Fin InclusionAI	72.2	–
51	MiMo-V2.5 Xiaomi	70.6	–
52	Qwen3.7 Plus Alibaba	70.5	Testar agora
53	DeepSeek V4 Flash 0420 DeepSeek	70.0	Testar agora
54	GLM-5.1 Z AI	69.3	Testar agora
55	GPT-5.4 nano OpenAI	69.2	Testar agora
56	GPT-5.4 mini OpenAI	69.2	Testar agora
57	Inkling Small Thinking Machines	68.5	–
58	Solar Pro 4 Upstage	68.4	–
59	Qwen3.6 Plus Alibaba	67.8	Testar agora
60	JT-4.1 Flash 236B A21B China Mobile	67.6	–
61	Qwen3.6 27B Alibaba	67.4	Testar agora
62	Inkling Thinking Machines	67.4	–
63	Ling 3.0 Flash InclusionAI	66.2	–
64	Grok Build 0.1 0616 SpaceXAI	66.2	–
65	MiniMax-M2.7 MiniMax	65.5	Testar agora
66	Muse Glimmer Meta	64.6	Testar agora
67	Gemini 3.5 Flash-Lite Google	64.5	Testar agora
68	Nemotron 3 Ultra 550B A55B NVIDIA	63.6	Testar agora
69	Claude 4.5 Sonnet Anthropic	61.6	Testar agora
70	MiMo-V2-Flash Xiaomi	60.7	Testar agora
71	Solar Open2 250B Upstage	60.5	–
72	Mistral Medium 3.5 Mistral	60.4	Testar agora
73	Qwen3.5 397B A17B Alibaba	60.3	Testar agora
74	LongCat 2.0 LongCat	59.9	–
75	GPT-5.1 OpenAI	59.7	Testar agora
76	Kimi K2.5 Kimi	58.4	Testar agora
77	Qwen3.5 122B A10B Alibaba	57.8	Testar agora
78	Ring-2.6-1T InclusionAI	56.2	–
79	Gemma 4 31B Google	56.1	Testar agora
80	GLM-4.7 Z AI	56.1	Testar agora
81	K-EXAONE 2.0 0803 LG AI Research	55.8	–
82	Grok 4.3 SpaceXAI	55.4	–
83	GLM-4.6 Z AI	55.0	Testar agora
84	Qwen3.6 35B A3B Alibaba	54.9	Testar agora
85	DeepSeek V3.2 DeepSeek	54.5	Testar agora
86	K2 Horizon 7B Institute of Foundation Models	54.2	–
87	A.X-K2 SK Telecom	54.0	–
88	GPT-5.5 Instant OpenAI	53.6	Testar agora
89	Gemini 2.5 Pro Preview Google	53.6	Testar agora
90	Step 3.7 Flash StepFun	53.3	Testar agora
91	Claude 4.5 Haiku Anthropic	53.3	Testar agora
92	DeepSeek V3.1 Terminus DeepSeek	52.4	Testar agora
93	Gemma 4 26B A4B Google	51.8	Testar agora
94	North Mini Code Cohere	50.3	Testar agora
95	Nemotron 3 Super 120B A12B NVIDIA	49.7	Testar agora
96	Qwen3.5 35B A3B Alibaba	48.7	Testar agora
97	G9v3-39A5B AI9Stars	48.1	–
98	Qwen3 Coder Next Alibaba	47.4	Testar agora
99	Gemini 3.1 Flash-Lite Google	46.4	Testar agora
100	o1 OpenAI	46.2	Testar agora

Como funciona a pontuação — AIM Index

● Capacidade 85%● Recência 15%

SWE-bench VerifiedAider PolyglotLiveCodeBench

Fontes de dados (1)

Artificial Analysis ↗