Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	Kimi K3 (Max)OpenMoonshot AI	1,488	±4	36,780	$6.0
2	—	GLM-5.3 (Max)OpenZ.ai	1,481	±5	26,606	$2.2
3	—	MiMo-V2.6-ProOpenXiaomi	1,480	±9	4,037	$0.54
4	▲ 1	GLM-5.3-FlashOpenZ.ai	1,477	±5	41,642	$0.24
5	▼ 1	DeepSeek-V4.1-Flash-20260910 (Max)OpenDeepSeek	1,476	±6	13,657	—
6	—	GLM-5.2 (Max)OpenZ.ai	1,475	±4	53,702	—
7	—	MiMo-V2.5-ProOpenXiaomi	1,467	±4	77,728	—
8	—	GLM-5.1OpenZ.ai	1,465	±4	66,771	—
9	—	DeepSeek-V4-Pro (High, 20260813)OpenDeepSeek · 1 more variant	1,465	±7	9,787	—
10	—	Kimi K2.6OpenMoonshot AI	1,461	±4	39,978	—
11	—	GLM-5OpenZ.ai	1,457	±4	29,255	—
12	—	DeepSeek-V4-Pro Preview (High)OpenDeepSeek	1,455	±4	54,870	—
13	—	Hy3OpenTencent	1,454	±6	13,840	—
14	—	Gemma 4 31BOpenGoogle	1,452	±7	6,138	$0.000
15	—	Kimi K2.5 (Thinking)OpenMoonshot AI · 1 more variant	1,450	±3	74,682	—
16	—	MiMo-V2.6-FlashOpenXiaomi	1,448	±6	15,312	$0.18
17	▲ 1	InklingOpenThinking Machines	1,442	±4	45,472	$1.8
18	▼ 1	Qwen3.5-397B-A17BOpenAlibaba	1,441	±3	97,675	—
19	—	GLM-4.7OpenZ.ai	1,441	±6	12,239	—
20	—	MiniMax-M3OpenMiniMax	1,439	±4	68,611	$0.52
21	—	DeepSeek-V4-Flash Preview (High)OpenDeepSeek	1,439	±4	51,763	—
22	—	Gemma 4 26B A4BOpenGoogle	1,438	±7	6,090	—
23	▲ 2	DeepSeek-V4-FlashOpenDeepSeek	1,436	±4	51,944	—
24	—	Beam 1.0 501B A23BOpenReflection	1,436	±9	4,233	—
25	▼ 2	Qwen3.8-27BOpenAlibaba	1,436	±5	27,779	$1.1
26	—	MiMo-V2.5OpenXiaomi	1,434	±4	47,327	—
27	—	Kimi K2 Thinking TurboOpenMoonshot AI	1,430	±3	63,310	—
28	▲ 1	NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)OpenNVIDIA	1,427	±7	11,563	—
29	▼ 1	Mistral Medium 3.5OpenMistral	1,426	±6	11,791	$3.0
30	—	DeepSeek-V3.2-Exp (Thinking)OpenDeepSeek · 1 more variant	1,425	±7	8,991	—
31	▲ 1	Muse GlimmerOpenMeta	1,425	±10	3,884	$0.52
32	▼ 1	DeepSeek-V3.2OpenDeepSeek · 1 more variant	1,425	±3	48,095	—
33	—	GLM-4.6OpenZ.ai	1,424	±4	35,810	—
34	—	Qwen3-235B-A22B-Instruct (2507)OpenAlibaba	1,422	±3	98,081	—
35	—	DeepSeek-R1 (0528)OpenDeepSeek · 1 more variant	1,421	±6	18,165	—
36	—	Kimi K2 Preview (0905)OpenMoonshot AI · 1 more variant	1,418	±7	11,592	—
37	—	DeepSeek-V3.1OpenDeepSeek · 1 more variant	1,417	±6	14,606	—
38	—	Qwen3.5-122B-A10BOpenAlibaba	1,416	±4	29,712	—
39	—	DeepSeek-V3.1-Terminus (Thinking)OpenDeepSeek · 1 more variant	1,416	±10	3,379	—
40	—	MiniMax-M2.7OpenMiniMax	1,415	±3	89,197	—
41	—	Mistral Large 3OpenMistral	1,414	±3	88,325	—
42	—	Qwen3-VL-235B-A22B-InstructOpenAlibaba	1,413	±7	11,314	—
43	—	NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)OpenNVIDIA	1,412	±9	4,178	—
44	—	GLM-4.5OpenZ.ai	1,411	±5	23,797	—
45	▲ 1	Qwen3.5-27BOpenAlibaba	1,409	±4	28,647	—
46	▼ 1	Hy3 previewOpenTencent	1,409	±7	6,869	—
47	—	Inkling-SmallOpenThinking Machines	1,406	±5	36,999	$0.52
48	—	Qwen3-235B-A22B (Non-Thinking)OpenAlibaba · 1 more variant	1,402	±5	37,472	—
49	—	LongCat-Flash-ChatOpenMeituan	1,401	±6	11,167	—
50	—	Qwen3-235B-A22B-Thinking (2507)OpenAlibaba	1,400	±7	8,822	—
51	—	Qwen3-Next-80B-A3B-InstructOpenAlibaba	1,399	±5	22,753	—
52	—	DeepSeek-V3 (0324)OpenDeepSeek · 1 more variant	1,395	±4	44,977	—
53	—	Qwen3-VL-235B-A22B-ThinkingOpenAlibaba	1,395	±7	7,862	—
54	—	Qwen3.5-35B-A3BOpenAlibaba	1,394	±4	30,427	—
55	—	Step-3.5-FlashOpenStepFun	1,393	±4	60,305	—
56	—	MiMo-V2-Flash (Non-Thinking)OpenXiaomi · 1 more variant	1,392	±3	48,060	—
57	—	MiniMax-M2.5OpenMiniMax	1,391	±4	42,783	—
58	—	Qwen3-Coder-480B-A35B-InstructOpenAlibaba	1,388	±5	25,190	—
59	—	MiniMax-M2.1 PreviewOpenMiniMax	1,385	±5	17,222	—
60	—	Qwen3-30B-A3B-Instruct (2507)OpenAlibaba	1,382	±5	23,312	—
61	—	Trinity Large PreviewOpen	1,379	±4	31,233	—
62	—	GLM-4.6VOpenZ.ai	1,378	±11	2,833	—
63	—	GLM-4.5-AirOpenZ.ai	1,373	±4	30,652	—
64	—	Qwen3-Next-80B-A3B-ThinkingOpenAlibaba	1,369	±6	13,476	—
65	—	Trinity Large ThinkingOpen	1,367	±5	30,290	—
66	—	Gemma 3 27B ITOpenGoogle	1,365	±4	46,670	—
67	—	GLM-4.7-FlashOpenZ.ai	1,365	±6	12,008	—
68	—	MiniMax-M1OpenMiniMax	1,364	±4	34,293	—
69	—	NVIDIA-Nemotron-3-Super-120B-A12BOpenNVIDIA	1,360	±7	7,870	—
70	—	Mistral Small 3.2 (2506)OpenMistral	1,356	±5	17,462	—
71	—	INTELLECT-3Open	1,356	±8	5,435	—
72	—	Command A (03-2025)OpenCohere	1,354	±3	55,763	$0.000
73	—	NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)OpenNVIDIA	1,353	±5	24,230	—
74	—	GLM-4.5VOpenZ.ai	1,352	±8	4,817	—
75	—	gpt-oss-120bOpenOpenAI	1,352	±4	30,200	$0.26
76	—	Step-3OpenStepFun	1,349	±8	6,291	—
77	—	Llama 3.1 Nemotron Ultra 253B v1OpenNVIDIA	1,348	±12	2,549	—
78	—	Qwen3-32BOpenAlibaba	1,347	±9	3,926	—
79	—	MiniMax-M2OpenMiniMax	1,344	±8	6,850	—
80	—	Ling-flash-2.0OpenAnt Group	1,343	±7	6,952	—
81	—	Llama 3.3 Nemotron Super 49B v1.5OpenNVIDIA	1,343	±10	3,327	—
82	—	Gemma 3 12B ITOpenGoogle	1,342	±10	3,829	—
83	—	Granite 4.2 30BOpenIBM	1,340	±10	3,389	—
84	—	QwQ-32BOpenAlibaba	1,336	±4	25,177	—
85	—	Llama 3.1 405B Instruct (BF16)OpenMeta · 1 more variant	1,335	±4	41,375	—
86	—	Olmo 3.1 32B InstructOpenAi2	1,329	±6	11,805	—
87	—	Llama 3.3 Nemotron Super 49B v1OpenNVIDIA	1,328	±12	2,218	—
88	—	Llama 4 Maverick 17B 128E InstructOpenMeta	1,327	±4	39,439	—
89	—	Qwen3-30B-A3BOpenAlibaba	1,327	±5	26,156	—
90	—	DeepSeek-V2.5 (1210)OpenDeepSeek · 1 more variant	1,323	±8	6,795	—
91	—	Ring-flash-2.0OpenAnt Group	1,322	±7	6,987	—
92	▲ 1	Llama 4 Scout 17B 16E InstructOpenMeta	1,321	±5	29,823	—
93	▼ 1	Molmo 2 8BOpenAi2	1,321	±21	822	—
94	—	Qwen-Max (0919)OpenAlibaba	1,318	±6	16,478	—
95	—	Llama 3.3 70B InstructOpenMeta	1,318	±4	54,493	—
96	—	Gemma 3n E4B ITOpenGoogle	1,318	±5	22,136	—
97	—	gpt-oss-20bOpenOpenAI	1,317	±6	10,416	—
98	—	Mistral Large 2 (2407)OpenMistral	1,314	±4	45,459	—
99	—	Athene V2 ChatOpen	1,314	±5	24,739	—
100	—	NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)OpenNVIDIA	1,314	±5	15,761	—
101	—	Athene 70B (0725)Open	1,307	±6	19,621	—
102	—	Olmo 3 32B ThinkOpenAi2	1,306	±8	5,827	—
103	—	Mistral Large (2411)OpenMistral	1,306	±4	28,073	—
104	—	Granite 4.1 8BOpenIBM	1,304	±10	4,177	—
105	—	Gemma 3 4B ITOpenGoogle	1,303	±9	4,171	—
106	—	Qwen2.5-72B-InstructOpenAlibaba	1,303	±4	39,406	—
107	—	Mistral Small 3.1 24B Instruct (2503)OpenMistral	1,303	±5	32,722	—
108	—	Llama 3.1 Nemotron 70B InstructOpenNVIDIA	1,299	±8	7,140	—
109	—	Llama 3.1 70B InstructOpenMeta	1,293	±4	55,240	—
110	—	Granite 4.2 3BOpenIBM	1,290	±12	3,249	—
111	—	Granite 4.2 8BOpenIBM	1,290	±11	3,251	$0.11
112	—	Gemma 2 27B ITOpenGoogle	1,289	±3	75,754	—
113	—	Jamba 1.5 LargeOpen	1,289	±7	8,662	—
114	—	Granite-4.0-H-SmallOpenIBM	1,287	±8	5,630	—
115	—	Llama 3.1 Nemotron 51B InstructOpenNVIDIA	1,287	±10	3,749	—
116	—	Olmo 3.1 32B ThinkOpenAi2	1,286	±7	8,299	—
117	—	Llama 3.1 Tulu 3 70BOpenAi2	1,286	±10	2,846	—
118	—	Gemma 2 9B IT SimPOOpen	1,280	±7	10,072	—
119	—	Nemotron-4 340B InstructOpenNVIDIA	1,277	±5	19,659	—
120	—	Llama 3 70B InstructOpenMeta	1,277	±4	156,876	—
121	—	Command R+ (08-2024)OpenCohere · 3 more variants	1,276	±7	9,866	—
122	—	Mistral Small 24B Instruct (2501)OpenMistral	1,274	±6	14,681	—
123	—	Qwen2.5-Coder-32B-InstructOpenAlibaba	1,271	±8	5,432	—
124	—	Aya Expanse 32BOpenCohere	1,267	±5	27,124	—
125	—	Gemma 2 9B ITOpenGoogle	1,267	±4	54,611	—
126	—	DeepSeek-Coder-V2OpenDeepSeek	1,265	±6	15,147	—
127	—	Qwen2-72B-InstructOpenAlibaba	1,262	±5	37,325	—
128	—	Phi-4OpenMicrosoft	1,256	±5	24,126	—
129	—	OLMo 2 32B Instruct (0325)OpenAi2	1,252	±11	3,334	—
130	—	Jamba 1.5 MiniOpen	1,240	±7	8,858	—
131	—	Ministral 8B (2410)OpenMistral	1,238	±9	4,781	—
132	—	Qwen1.5-110B-ChatOpenAlibaba	1,234	±6	26,195	—
133	—	Qwen1.5-72B-ChatOpenAlibaba	1,234	±5	39,302	—
134	—	Mixtral 8x22B Instruct v0.1OpenMistral	1,230	±5	51,416	—
135	—	Llama 3 8B InstructOpenMeta	1,224	±4	104,642	—
136	—	Aya Expanse 8BOpenCohere	1,223	±7	9,818	—
137	—	Llama 3.1 Tulu 3 8BOpenAi2	1,221	±11	2,896	—
138	—	Zephyr ORPO 141B A35B v0.1Open	1,213	±11	4,652	—
139	—	Yi 1.5 34B ChatOpen	1,213	±5	24,146	—
140	—	Llama 3.1 8B InstructOpenMeta	1,211	±4	49,605	—
141	—	Granite 3.1 8B InstructOpenIBM	1,209	±11	3,090	—
142	—	Qwen1.5-32B-ChatOpenAlibaba	1,204	±6	21,741	—
143	—	Gemma 2 2B ITOpenGoogle	1,200	±4	46,616	—
144	—	Phi-3 Medium 4K InstructOpenMicrosoft	1,198	±5	25,055	—
145	—	Mixtral 8x7B Instruct v0.1OpenMistral	1,197	±4	73,503	—
146	—	DBRX Instruct PreviewOpen	1,196	±6	32,191	—
147	—	Qwen1.5-14B-ChatOpenAlibaba	1,191	±7	17,839	—
148	—	InternLM2.5 20B ChatOpen	1,191	±7	9,901	—
149	—	DeepSeek LLM 67B ChatOpenDeepSeek	1,185	±11	4,932	—
150	—	WizardLM 70BOpenMicrosoft	1,185	±9	8,214	—
151	—	Yi 34B ChatOpen	1,184	±7	15,483	—
152	—	Granite 3.0 8B InstructOpenIBM	1,183	±9	6,638	—
153	—	OpenChat 3.5Open · 1 more variant	1,183	±10	7,968	—
154	—	Gemma 1.1 7B ITOpenGoogle	1,183	±6	23,893	—
155	—	Snowflake Arctic InstructOpen	1,180	±6	32,832	—
156	—	Granite 3.1 2B InstructOpenIBM	1,179	±11	3,188	—
157	—	Tulu 2 DPO 70BOpen	1,178	±10	6,535	—
158	—	OpenHermes 2.5 Mistral 7BOpen	1,176	±10	5,006	—
159	—	Vicuna 33BOpen	1,173	±6	22,479	—
160	—	Phi-3 Small 8K InstructOpenMicrosoft	1,171	±6	17,766	—
161	—	Starling LM 7B BetaOpen	1,171	±7	16,056	—
162	—	Llama 2 70B ChatOpenMeta	1,171	±5	38,492	—
163	—	Starling LM 7B AlphaOpen	1,167	±8	10,224	—
164	—	Llama 3.2 3B InstructOpenMeta	1,167	±8	7,936	—
165	—	Nous Hermes 2 Mixtral 8x7B DPOOpen	1,164	±12	3,777	—
166	—	Granite 3.0 2B InstructOpenIBM	1,157	±8	6,837	—
167	—	Llama 2 70B SteerLM ChatOpenNVIDIA	1,155	±13	3,585	—
168	—	QwQ-32B-PreviewOpenAlibaba	1,154	±11	3,231	—
169	—	SOLAR 10.7B Instruct v1.0OpenUpstage	1,152	±13	4,155	—
170	—	Dolphin 2.2.1 Mistral 7BOpen	1,152	±15	1,679	—
171	—	MPT 30B ChatOpen	1,151	±12	2,572	—
172	—	WizardLM 13BOpenMicrosoft	1,150	±9	7,044	—
173	—	Mistral 7B Instruct v0.2OpenMistral	1,149	±7	19,402	—
174	—	Falcon 180B ChatOpen	1,148	±17	1,295	—
175	—	Qwen1.5-7B-ChatOpenAlibaba	1,144	±10	4,737	—
176	—	Phi-3 Mini 4K Instruct (June 2024)OpenMicrosoft · 1 more variant	1,143	±6	12,297	—
177	—	Vicuna 13BOpen	1,142	±7	19,367	—
178	—	Llama 2 13B ChatOpenMeta	1,141	±7	19,174	—
179	—	Qwen-14B-ChatOpenAlibaba	1,139	±11	4,964	—
180	—	Gemma 7B ITOpenGoogle	1,138	±9	8,925	—
181	—	Code Llama 34B InstructOpenMeta	1,137	±9	7,366	—
182	—	Zephyr 7B BetaOpen	1,131	±9	11,118	—
183	—	Phi-3 Mini 128K InstructOpenMicrosoft	1,130	±7	20,685	—
184	—	Guanaco 33BOpen	1,128	±12	2,921	—
185	—	Zephyr 7B AlphaOpen	1,127	±16	1,785	—
186	—	StripedHyena Nous 7BOpen	1,122	±11	5,182	—
187	—	Code Llama 70B InstructOpenMeta	1,119	±18	1,143	—
188	—	Gemma 1.1 2B ITOpenGoogle	1,117	±8	10,854	—
189	—	Vicuna 7BOpen	1,115	±9	6,923	—
190	—	SmolLM2 1.7B InstructOpen	1,115	±14	2,199	—
191	—	Llama 3.2 1B InstructOpenMeta	1,111	±8	8,045	—
192	—	Mistral 7B InstructOpenMistral	1,110	±9	8,977	—
193	—	Llama 2 7B ChatOpenMeta	1,108	±7	14,148	—
194	—	Gemma 2B ITOpenGoogle	1,094	±11	4,780	—
195	—	Qwen1.5-4B-ChatOpenAlibaba	1,091	±9	7,597	—
196	—	OLMo 7B InstructOpenAi2	1,074	±11	6,328	—
197	—	Koala 13BOpen	1,071	±10	6,965	—
198	—	Alpaca 13BOpen	1,070	±11	5,745	—
199	—	GPT4All 13B SnoozyOpen	1,068	±15	1,743	—
200	—	MPT 7B ChatOpen	1,064	±12	3,924	—
201	—	ChatGLM3 6BOpen	1,057	±12	4,658	—
202	—	RWKV-4 Raven 14BOpen	1,042	±11	4,845	—
203	—	ChatGLM2 6BOpen	1,025	±14	2,658	—
204	—	OpenAssistant Pythia 12BOpen	1,024	±11	6,310	—
205	—	ChatGLM 6BOpen	996	±12	4,914	—
206	—	FastChat-T5 3BOpen	993	±12	4,203	—
207	—	Dolly 2.0 12BOpen	983	±13	3,412	—
208	—	LLaMA 13BOpenMeta	975	±16	2,391	—
209	—	StableLM Tuned Alpha 7BOpen	953	±13	3,287	—

159 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