Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Kimi K3 (max)OpenKimi · 1 more variant	59.7	$6.0	34	3.8 s
2	—	Qwen3.8 2.4T A95BOpenAlibaba	57.7	$3.0	62	2.5 s
3	—	DeepSeek V4 Pro 0813 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	53.2	$2.0	70	1.8 s
4	—	GLM-5.2 (max)OpenZ AI · 1 more variant	52.6	$2.2	—	—
5	—	Qwen3.8 27B (xhigh)OpenAlibaba · 2 more variants	52.0	$1.1	53	3.0 s
6	—	DeepSeek V4 Flash 0731 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	51.8	$0.66	122	1.1 s
7	—	MiniMax-M3OpenMiniMax	45.4	$0.52	103	1.3 s
8	—	Kimi K2.6OpenKimi · 1 more variant	45.1	$1.7	48	2.8 s
9	—	Kimi K2.7 CodeOpenKimi	43.0	$1.7	49	2.9 s
10	—	MiMo-V2.5-ProOpenXiaomi · 1 more variant	42.9	$0.54	52	3.1 s
11	—	Hy3OpenTencent	42.2	$0.24	78	2.9 s
12	—	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	41.0	$2.1	82	1.4 s
13	—	GLM-5 (Reasoning)OpenZ AI · 1 more variant	40.6	$1.6	75	1.3 s
14	—	MiniMax-M2.7OpenMiniMax	38.9	$0.52	62	1.7 s
15	—	MiMo-V2.5OpenXiaomi	38.0	$0.18	67	4.2 s
16	—	Ling 3.0 FlashOpenInclusionAI	37.8	$0.11	394	2.4 s
17	—	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	37.7	$1.4	58	3.7 s
18	—	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	36.0	$1.2	61	2.8 s
19	—	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	34.6	$0.83	77	5.6 s
20	—	MiniMax-M2.5OpenMiniMax	34.5	$0.52	102	1.7 s
21	—	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	34.5	$1.0	97	1.1 s
22	—	Hy3-preview (Reasoning)OpenTencent · 1 more variant	34.4	$0.100	—	—
23	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	34.3	$1.4	79	2.1 s
24	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	34.0	—	—	—
25	—	LongCat 2.0OpenLongCat	34.0	$1.3	44	2.8 s
26	—	Kimi K2 ThinkingOpenKimi	33.5	$1.1	115	1.4 s
27	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	32.8	$1.1	129	2.3 s
28	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	32.8	$0.32	—	—
29	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	32.1	$0.84	121	2.1 s
30	—	MiniMax-M2.1OpenMiniMax	32.1	$0.52	99	1.7 s
31	—	Ring-2.6-1TOpenInclusionAI	31.7	$0.85	130	4.1 s
32	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	31.4	$1.9	—	—
33	—	Step 3.7 FlashOpenStepFun	30.9	$0.44	131	2.7 s
34	—	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	29.9	$0.69	150	2.1 s
35	—	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	29.3	$0.96	49	2.3 s
36	—	MiniMax-M2OpenMiniMax	28.9	$0.52	93	1.7 s
37	—	Ling-2.6-1TOpenInclusionAI	26.6	$0.85	—	—
38	—	Step 3.5 FlashOpenStepFun	26.0	$0.15	247	1.0 s
39	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	25.9	$0.32	—	—
40	—	Ling 3.0 TinyOpenInclusionAI	24.5	$0.000	162	2.7 s
41	—	Kimi K2 0905OpenKimi · 1 more variant	24.0	$1.1	41	1.1 s
42	—	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	23.3	$0.15	97	1.2 s
43	—	DeepSeek V3.2 SpecialeOpenDeepSeek	22.6	—	—	—
44	—	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	21.8	$0.15	78	1.8 s
45	—	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	21.4	$0.84	—	—
46	—	Qwen3 Coder NextOpenAlibaba	21.3	$0.56	146	1.0 s
47	—	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.9	$1.3	58	2.8 s
48	—	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	20.4	$0.060	21	0.8 s
49	—	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	20.4	$1.8	—	—
50	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	19.9	$0.75	70	2.7 s
51	—	GLM-4.5 (Reasoning)OpenZ AI	19.7	—	—	—
52	—	Seed-OSS-36B-InstructOpenByteDance Seed	18.5	$0.30	32	2.9 s
53	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.4	$0.40	62	2.0 s
54	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.2	$3.0	72	2.9 s
55	—	Qwen3 VL 32B (Reasoning)OpenAlibaba	18.1	$0.28	90	2.5 s
56	—	MiniMax M1 80kOpenMiniMax	17.9	$0.96	—	—
57	—	LongCat Flash LiteOpenLongCat	17.4	—	—	—
58	—	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	16.9	$0.45	59	4.0 s
59	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	16.9	$0.41	203	2.2 s
60	—	GLM-4.5-AirOpenZ AI	16.7	$0.37	45	2.9 s
61	—	Ring-1TOpenInclusionAI	16.3	—	—	—
62	—	DeepSeek V3 0324OpenDeepSeek · 1 more variant	15.2	$0.48	—	—
63	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	14.6	$0.75	167	2.3 s
64	—	MiniMax M1 40kOpenMiniMax	14.5	—	—	—
65	—	Qwen3 VL 235B A22B InstructOpenAlibaba	14.4	$0.70	50	2.8 s
66	—	Ling 2.6 FlashOpenInclusionAI	14.2	$0.15	104	1.1 s
67	—	Qwen3 Next 80B A3B InstructOpenAlibaba	13.8	$0.41	189	2.1 s
68	—	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.90	96	2.6 s
69	—	QwQ 32BOpenAlibaba	13.4	$0.75	—	—
70	—	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.4	$0.75	112	2.2 s
71	—	Ling-1TOpenInclusionAI	12.7	—	—	—
72	—	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	11.9	—	—	—
73	—	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	11.4	$0.28	105	2.4 s
74	—	Qwen3 VL 32B InstructOpenAlibaba	11.0	$0.28	64	2.6 s
75	—	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
76	—	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.5	$0.66	115	2.3 s
77	—	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	10.4	$1.3	61	2.7 s
78	—	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.3	—	—	—
79	—	Qwen3 VL 30B A3B InstructOpenAlibaba	9.9	$0.35	111	2.1 s
80	—	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.8	$0.80	29	0.8 s
81	—	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.7	—	—	—
82	—	Ling-flash-2.0OpenInclusionAI	9.6	$0.25	57	2.6 s
83	—	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.5	$0.43	101	1.9 s
84	—	Qwen2.5 Instruct 72BOpenAlibaba	9.4	$0.48	—	—
85	—	Step3 VL 10BOpenStepFun	9.3	—	—	—
86	—	QwQ 32B-PreviewOpenAlibaba	9.1	—	—	—
87	—	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	9.0	$0.90	90	1.7 s
88	—	Qwen3 30B A3B 2507 InstructOpenAlibaba	8.9	$0.35	144	1.9 s
89	—	ERNIE 4.5 300B A47BOpenBaidu	8.9	$0.49	—	—
90	—	Kimi Linear 48B A3B InstructOpenKimi	8.4	—	—	—
91	—	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	8.3	$0.66	41	3.7 s
92	—	Qwen3 VL 8B InstructOpenAlibaba	8.2	$0.31	116	2.2 s
93	—	Ring-flash-2.0OpenInclusionAI	8.0	$0.25	—	—
94	—	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.7	—	—	—
95	—	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	7.4	—	—	—
96	—	Qwen2.5 Instruct 32BOpenAlibaba	7.2	—	—	—
97	—	Qwen3 4B 2507 InstructOpenAlibaba	6.9	—	—	—
98	—	Qwen2.5 Coder Instruct 32BOpenAlibaba	6.9	—	—	—
99	—	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.5	—	—	—
100	—	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.2	—	—	—
101	—	Qwen2 Instruct 72BOpenAlibaba	5.7	—	—	—
102	—	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	5.2	—	—	—
103	—	Qwen3 Omni 30B A3B InstructOpenAlibaba	4.8	$0.43	95	1.9 s
104	—	DeepSeek-Coder-V2OpenDeepSeek	4.7	—	—	—
105	—	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.1	—	—	—
106	—	Qwen3 VL 4B InstructOpenAlibaba	3.7	—	—	—
107	—	Qwen1.5 Chat 110BOpenAlibaba	3.7	—	—	—
108	—	Ling-mini-2.0OpenInclusionAI	3.4	—	—	—
109	—	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.3	—	—	—
110	—	DeepSeek-V2-ChatOpenDeepSeek	3.3	—	—	—
111	—	Qwen Chat 72BOpenAlibaba	3.0	—	—	—
112	—	DeepSeek Coder V2 Lite InstructOpenDeepSeek	2.7	—	—	—
113	—	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	2.6	—	—	—
114	—	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	2.2	—	—	—
115	—	Qwen Chat 14BOpenAlibaba	1.7	—	—	—
116	—	Qwen3 0.6B (Non-reasoning)OpenAlibaba · 1 more variant	1.0	—	—	—

66 more models

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026

64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi