Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Kimi K3 (max)OpenKimi · 1 more variant	57.1	$6.0	35	2.8 s
2	—	GLM-5.2 (max)OpenZ AI · 1 more variant	51.1	$2.2	173	1.5 s
3	▲ 8	DeepSeek V4 Flash 0731 (Reasoning, Max Effort)OpenDeepSeek · 3 more variants	49.9	$0.18	—	—
4	▼ 1	Qwen3.7 MaxClosedAlibaba	46.0	$3.8	206	2.4 s
5	▼ 1	MiniMax-M3OpenMiniMax	44.4	$0.52	85	1.3 s
6	▼ 1	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	44.3	$0.54	55	1.6 s
7	▼ 1	Kimi K2.6OpenKimi · 1 more variant	44.2	$1.7	39	2.8 s
8	▼ 1	MiMo-V2.5-ProOpenXiaomi · 1 more variant	42.2	$0.54	39	2.7 s
9	▼ 1	Kimi K2.7 CodeOpenKimi	41.9	$1.7	40	3.2 s
10	▼ 1	Hy3OpenTencent	41.2	$0.24	72	2.7 s
11	▼ 1	MiMo-V2-ProClosedXiaomi	40.3	—	—	—
12	—	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	40.2	$2.1	72	1.6 s
13	—	Qwen3.6 Max PreviewClosedAlibaba	40.0	$2.9	54	3.4 s
14	—	Qwen3.6 PlusClosedAlibaba	39.6	$1.1	56	2.1 s
15	—	GLM-5 (Reasoning)OpenZ AI · 1 more variant	39.5	$1.6	43	1.7 s
16	—	Qwen3.7 PlusClosedAlibaba	39.0	$0.70	53	2.8 s
17	—	MiniMax-M2.7OpenMiniMax	38.1	$0.52	95	1.5 s
18	—	GLM-5-TurboClosedZ AI	38.1	—	—	—
19	—	MiMo-V2.5OpenXiaomi	37.2	$0.18	73	3.0 s
20	—	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	37.1	$1.4	58	3.7 s
21	—	MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant	36.4	—	—	—
22	—	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	35.4	$1.2	61	2.8 s
23	—	GLM 5V Turbo (Reasoning)ClosedZ AI	34.5	—	—	—
24	—	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	33.8	$0.83	77	5.6 s
25	—	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	33.7	$1.0	112	1.1 s
26	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	33.7	$1.4	67	2.4 s
27	—	MiniMax-M2.5OpenMiniMax	33.7	$0.52	77	1.7 s
28	—	Hy3-preview (Reasoning)OpenTencent · 1 more variant	33.6	$0.11	—	—
29	—	LongCat 2.0OpenLongCat	33.5	$1.3	43	2.7 s
30	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	33.2	—	—	—
31	—	Kimi K2 ThinkingOpenKimi	32.7	$1.1	122	1.4 s
32	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	32.3	$1.1	136	2.4 s
33	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	32.0	$0.32	—	—
34	—	Qwen3 Max ThinkingClosedAlibaba · 1 more variant	31.7	—	—	—
35	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	31.6	$0.56	165	2.2 s
36	—	MiniMax-M2.1OpenMiniMax	31.4	$0.52	79	1.6 s
37	—	Qwen3.5 Omni PlusClosedAlibaba	30.6	$1.5	52	2.5 s
38	—	Ring-2.6-1TOpenInclusionAI	30.6	$0.85	125	3.0 s
39	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	30.4	$1.9	—	—
40	—	Step 3.7 FlashOpenStepFun	30.3	$0.44	410	1.1 s
41	—	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	29.3	$0.69	154	2.1 s
42	—	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	28.7	$0.96	53	2.3 s
43	—	MiniMax-M2OpenMiniMax	28.3	$0.52	67	1.8 s
44	—	Ling-2.6-1TOpenInclusionAI	26.1	$0.85	—	—
45	—	Step 3.5 Flash 2603ClosedStepFun · 1 more variant	26.0	$0.15	216	1.0 s
46	—	Doubao Seed CodeClosedByteDance Seed	26.0	—	—	—
47	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	25.4	$0.32	—	—
48	—	Qwen3 MaxClosedAlibaba · 1 more variant	24.0	$2.4	63	2.3 s
49	—	Kimi K2 0905OpenKimi · 1 more variant	23.5	$1.1	38	1.3 s
50	—	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	22.9	$0.15	97	1.1 s
51	—	DeepSeek V3.2 SpecialeOpenDeepSeek	22.2	—	—	—
52	—	ERNIE 5.0 Thinking PreviewClosedBaidu	21.9	—	—	—
53	—	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	21.4	$0.15	76	2.1 s
54	—	Qwen3 Coder NextOpenAlibaba	21.1	$0.56	142	1.7 s
55	—	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	21.0	$0.84	—	—
56	—	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	20.6	$2.6	56	2.9 s
57	—	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	20.1	$0.060	46	0.7 s
58	—	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	20.1	$2.1	—	—
59	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	19.6	$2.6	49	3.0 s
60	—	GLM-4.5 (Reasoning)OpenZ AI	19.5	—	—	—
61	—	Qwen3.5 Omni FlashClosedAlibaba	19.0	$0.28	238	2.1 s
62	—	Seed-OSS-36B-InstructOpenByteDance Seed	18.3	$0.30	34	3.0 s
63	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	18.2	$1.2	56	2.3 s
64	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	18.0	$3.0	65	3.0 s
65	—	Qwen3 VL 32B (Reasoning)OpenAlibaba	17.9	$2.6	87	2.8 s
66	—	MiniMax M1 80kOpenMiniMax	17.7	$0.96	—	—
67	—	LongCat Flash LiteOpenLongCat	17.2	—	—	—
68	—	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	16.8	$0.45	77	3.6 s
69	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	16.7	$1.9	203	2.3 s
70	—	GLM-4.5-AirOpenZ AI	16.5	$0.37	78	2.7 s
71	—	Ring-1TOpenInclusionAI	16.2	—	—	—
72	—	DeepSeek V3 0324OpenDeepSeek · 1 more variant	15.4	$0.48	—	—
73	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	14.4	$0.75	138	2.4 s
74	—	MiniMax M1 40kOpenMiniMax	14.4	—	—	—
75	—	Qwen3 VL 235B A22B InstructOpenAlibaba	14.3	$1.2	49	2.7 s
76	—	Ling 2.6 FlashOpenInclusionAI	14.1	$0.15	86	1.3 s
77	—	Qwen3 Next 80B A3B InstructOpenAlibaba	13.7	$0.88	179	2.2 s
78	—	Qwen3 Coder 30B A3B InstructOpenAlibaba	13.6	$0.90	92	2.5 s
79	—	QwQ 32BOpenAlibaba	13.4	$0.75	31	2.3 s
80	—	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	13.3	$0.75	109	2.2 s
81	—	Ling-1TOpenInclusionAI	12.8	—	—	—
82	—	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	12.0	—	—	—
83	—	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	11.5	$2.6	93	2.5 s
84	—	Qwen3 VL 32B InstructOpenAlibaba	11.1	$1.2	66	2.7 s
85	—	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	11.0	—	—	—
86	—	Qwen3 VL 8B (Reasoning)OpenAlibaba	10.6	$0.66	113	2.3 s
87	—	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	10.4	$1.3	47	3.4 s
88	—	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	10.4	—	—	—
89	—	Qwen2.5 MaxClosedAlibaba	10.2	—	—	—
90	—	Qwen3 VL 30B A3B InstructOpenAlibaba	10.0	$0.35	114	2.2 s
91	—	DeepSeek R1 Distill Llama 70BOpenDeepSeek	9.9	$0.79	28	0.9 s
92	—	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	9.8	—	—	—
93	—	Ling-flash-2.0OpenInclusionAI	9.7	$0.25	62	1.6 s
94	—	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	9.6	$0.43	99	2.0 s
95	—	Qwen2.5 Instruct 72BOpenAlibaba	9.6	$0.48	—	—
96	—	Step3 VL 10BOpenStepFun	9.5	—	—	—
97	—	QwQ 32B-PreviewOpenAlibaba	9.2	—	—	—
98	—	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	9.1	$0.90	86	1.7 s
99	—	Qwen3 30B A3B 2507 InstructOpenAlibaba	9.1	$0.35	152	1.9 s
100	—	ERNIE 4.5 300B A47BOpenBaidu	9.0	$0.49	—	—
101	—	Kimi Linear 48B A3B InstructOpenKimi	8.5	—	—	—
102	—	Qwen3 VL 8B InstructOpenAlibaba	8.4	$0.31	117	2.2 s
103	—	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	8.3	$0.66	41	3.7 s
104	—	Ring-flash-2.0OpenInclusionAI	8.2	$0.25	—	—
105	—	Qwen3 VL 4B (Reasoning)OpenAlibaba	7.9	—	—	—
106	▲ 3	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	7.6	—	—	—
107	▼ 1	Qwen2.5 Instruct 32BOpenAlibaba	7.5	—	—	—
108	▼ 1	Qwen3 4B 2507 InstructOpenAlibaba	7.1	—	—	—
109	▼ 1	Qwen2.5 Coder Instruct 32BOpenAlibaba	7.1	—	—	—
110	—	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	6.8	—	—	—
111	—	DeepSeek R1 Distill Llama 8BOpenDeepSeek	6.4	—	—	—
112	—	Qwen2.5 TurboClosedAlibaba	6.3	$0.088	107	2.1 s
113	—	Qwen2 Instruct 72BOpenAlibaba	6.0	—	—	—
114	—	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	5.5	—	—	—
115	—	Qwen3 Omni 30B A3B InstructOpenAlibaba	5.1	$0.43	95	1.8 s
116	—	DeepSeek-Coder-V2OpenDeepSeek	5.1	—	—	—
117	—	Qwen2.5 Coder Instruct 7BOpenAlibaba	4.5	—	—	—
118	—	Qwen3 VL 4B InstructOpenAlibaba	4.1	—	—	—
119	—	Qwen1.5 Chat 110BOpenAlibaba	4.1	—	—	—
120	—	Ling-mini-2.0OpenInclusionAI	3.8	—	—	—
121	—	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	3.7	—	—	—
122	—	DeepSeek-V2-ChatOpenDeepSeek	3.6	—	—	—
123	—	Qwen Chat 72BOpenAlibaba	3.4	—	—	—
124	—	DeepSeek Coder V2 Lite InstructOpenDeepSeek	3.1	—	—	—
125	—	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	3.0	—	—	—
126	—	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	2.6	—	—	—
127	—	Qwen Chat 14BOpenAlibaba	2.1	—	—	—
128	—	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	1.3	—	—	—

78 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