Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	deepseek-v3-0324OpenDeepSeek · 1 more variant	1,323	±9	6,792	—
2	—	deepseek-r1OpenDeepSeek	1,316	±4	16,857	—
3	—	gemma-3-27b-itOpenGoogle	1,282	±6	10,735	—
4	—	command-a-03-2025OpenCohere	1,264	±5	8,521	—
5	—	qwq-32bOpenAlibaba · 1 more variant	1,257	±6	8,563	—
6	—	llama-3.1-405b-instruct-bf16OpenMeta	1,254	±2	43,785	—
7	—	llama-3.1-405b-instruct-fp8OpenMeta	1,253	±2	63,056	—
8	—	llama-4-maverick-17b-128e-instructOpenMeta	1,250	±7	5,772	—
9	—	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,247	±11	2,368	—
10	—	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,240	±6	7,239	—
11	—	llama-3.3-70b-instructOpenMeta	1,235	±2	38,099	—
12	—	mistral-large-2407OpenMistral · 1 more variant	1,232	±2	48,214	—
13	—	qwen-max-0919OpenAlibaba	1,231	±4	17,438	—
14	—	athene-v2-chatOpenNexusFlow	1,231	±3	26,086	—
15	—	athene-70b-0725OpenNexusFlow	1,223	±4	20,580	—
16	—	qwen2.5-72b-instructOpenAlibaba	1,222	±2	41,532	—
17	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,217	±6	7,576	—
18	—	llama-3.1-70b-instructOpenMeta	1,214	±2	58,650	—
19	—	llama-3.1-tulu-3-70bOpenAi2	1,209	±9	3,011	—
20	—	gemma-2-27b-itOpenGoogle	1,207	±2	79,532	—
21	—	jamba-1.5-largeOpenAI21 Labs	1,206	±5	9,122	—
22	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,204	±8	3,889	—
23	—	gemma-2-9b-it-simpoOpenPrinceton	1,200	±5	10,548	—
24	—	command-r-plus-08-2024OpenCohere	1,197	±6	10,534	—
25	—	nemotron-4-340b-instructOpenNVIDIA	1,196	±4	20,614	—
26	—	llama-3-70b-instructOpenMeta	1,195	±2	163,662	—
27	—	mistral-small-24b-instruct-2501OpenMistral	1,192	±4	15,089	—
28	—	qwen2.5-coder-32b-instructOpenAlibaba	1,190	±6	5,731	—
29	—	c4ai-aya-expanse-32bOpenCohere	1,185	±3	28,752	—
30	—	command-r-plusOpenCohere	1,183	±2	80,848	—
31	—	deepseek-coder-v2OpenDeepSeek	1,182	±3	15,757	—
32	—	qwen2-72b-instructOpenAlibaba	1,181	±3	38,886	—
33	—	gemma-2-9b-itOpenGoogle	1,180	±2	57,206	—
34	—	phi-4OpenMicrosoft	1,177	±3	25,228	—
35	—	command-r-08-2024OpenCohere	1,176	±5	10,843	—
36	—	jamba-1.5-miniOpenAI21 Labs	1,160	±5	9,273	—
37	—	ministral-8b-2410OpenMistral	1,160	±6	5,108	—
38	—	qwen1.5-110b-chatOpenAlibaba	1,155	±3	27,438	—
39	—	c4ai-aya-expanse-8bOpenCohere	1,151	±5	10,397	—
40	—	mixtral-8x22b-instruct-v0.1OpenMistral	1,149	±3	53,758	—
41	—	qwen1.5-72b-chatOpenAlibaba	1,148	±3	40,670	—
42	—	command-rOpenCohere	1,148	±2	56,381	—
43	—	llama-3.1-tulu-3-8bOpenAi2	1,147	±9	3,076	—
44	—	llama-3-8b-instructOpenMeta	1,143	±2	109,091	—
45	—	granite-3.1-8b-instructOpenIBM	1,135	±8	3,293	—
46	—	yi-1.5-34b-chatOpen01 AI	1,134	±4	25,131	—
47	—	llama-3.1-8b-instructOpenMeta	1,133	±3	52,586	—
48	—	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,130	±6	4,860	—
49	—	qwen1.5-32b-chatOpenAlibaba	1,126	±4	22,757	—
50	—	phi-3-medium-4k-instructOpenMicrosoft	1,118	±4	26,109	—
51	—	gemma-2-2b-itOpenGoogle	1,118	±3	48,902	—
52	—	internlm2_5-20b-chatOpenInternLM	1,116	±5	10,596	—
53	—	mixtral-8x7b-instruct-v0.1OpenMistral	1,114	±2	76,140	—
54	—	dbrx-instruct-previewOpenDatabricks	1,113	±3	33,738	—
55	—	granite-3.0-8b-instructOpenIBM	1,110	±8	7,001	—
56	—	qwen1.5-14b-chatOpenAlibaba	1,107	±4	18,683	—
57	—	wizardlm-70bOpenMicrosoft	1,105	±6	8,385	—
58	—	granite-3.1-2b-instructOpenIBM	1,104	±8	3,383	—
59	—	snowflake-arctic-instructOpenSnowflake	1,102	±3	34,176	—
60	—	yi-34b-chatOpen01 AI	1,101	±5	15,918	—
61	—	openchat-3.5-0106OpenOpenChat · 1 more variant	1,101	±4	12,989	—
62	—	gemma-1.1-7b-itOpenGoogle	1,099	±4	25,068	—
63	—	phi-3-small-8k-instructOpenMicrosoft	1,098	±4	18,472	—
64	—	llama-3.2-3b-instructOpenMeta	1,094	±7	8,400	—
65	—	tulu-2-dpo-70bOpenAllenAI/UW	1,092	±7	6,658	—
66	—	starling-lm-7b-betaOpenNexusflow	1,092	±4	16,674	—
67	—	vicuna-33bOpenLMSYS	1,091	±4	22,946	—
68	—	deepseek-llm-67b-chatOpenDeepSeek	1,091	±9	4,988	—
69	—	openhermes-2.5-mistral-7bOpenNousResearch	1,089	±6	5,086	—
70	—	starling-lm-7b-alphaOpenUC Berkeley	1,083	±5	10,417	—
71	—	llama-2-70b-chatOpenMeta	1,082	±3	39,605	—
72	—	granite-3.0-2b-instructOpenIBM	1,082	±8	7,186	—
73	—	llama2-70b-steerlm-chatOpenNVIDIA	1,074	±11	3,636	—
74	—	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,072	±8	3,838	—
75	—	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,069	±13	1,713	—
76	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,067	±5	12,804	—
77	—	mistral-7b-instruct-v0.2OpenMistral	1,067	±4	20,066	—
78	—	solar-10.7b-instruct-v1.0OpenUpstage AI	1,066	±9	4,289	—
79	—	qwen1.5-7b-chatOpenAlibaba	1,065	±7	4,871	—
80	—	wizardlm-13bOpenMicrosoft	1,064	±6	7,176	—
81	—	mpt-30b-chatOpenMosaicML	1,060	±9	2,644	—
82	—	falcon-180b-chatOpenTII	1,059	±15	1,328	—
83	—	vicuna-13bOpenLMSYS	1,058	±5	19,771	—
84	—	qwen-14b-chatOpenAlibaba	1,056	±8	5,067	—
85	—	phi-3-mini-4k-instructOpenMicrosoft	1,056	±4	21,094	—
86	—	llama-2-13b-chatOpenMeta	1,054	±3	19,717	—
87	—	smollm2-1.7b-instructOpenHuggingFace	1,050	±12	2,377	—
88	—	zephyr-7b-betaOpenHuggingFace	1,049	±6	11,320	—
89	—	phi-3-mini-128k-instructOpenMicrosoft	1,049	±4	21,633	—
90	—	gemma-7b-itOpenGoogle	1,048	±6	9,176	—
91	—	codellama-34b-instructOpenMeta	1,047	±7	7,509	—
92	—	zephyr-7b-alphaOpenHuggingFace	1,045	±14	1,811	—
93	—	llama-3.2-1b-instructOpenMeta	1,044	±6	8,517	—
94	—	gemma-1.1-2b-itOpenGoogle	1,041	±6	11,348	—
95	—	guanaco-33bOpenUW	1,040	±11	2,997	—
96	—	codellama-70b-instructOpenMeta	1,039	±18	1,190	—
97	—	stripedhyena-nous-7bOpenTogether AI	1,034	±7	5,278	—
98	—	mistral-7b-instructOpenMistral	1,026	±5	9,143	—
99	—	llama-2-7b-chatOpenMeta	1,025	±4	14,532	—
100	—	vicuna-7bOpenLMSYS	1,021	±7	7,014	—
101	—	qwen1.5-4b-chatOpenAlibaba	1,014	±7	7,821	—
102	—	gemma-2b-itOpenGoogle	1,008	±8	4,921	—
103	—	olmo-7b-instructOpenAi2	994	±9	6,502	—
104	—	koala-13bOpenUC Berkeley	980	±7	7,021	—
105	—	chatglm3-6bOpenTsinghua	974	±9	4,761	—
106	—	gpt4all-13b-snoozyOpenNomic AI	974	±13	1,788	—
107	—	mpt-7b-chatOpenMosaicML	967	±9	3,996	—
108	—	alpaca-13bOpenStanford	967	±8	5,865	—
109	—	RWKV-4-Raven-14BOpenRWKV	949	±8	4,920	—
110	—	chatglm2-6bOpenTsinghua	942	±10	2,712	—
111	—	oasst-pythia-12bOpenOpenAssistant	931	±7	6,367	—
112	—	fastchat-t5-3bOpenLMSYS	896	±10	4,288	—
113	—	chatglm-6bOpenTsinghua	889	±10	4,987	—
114	—	dolly-v2-12bOpenDatabricks	882	±11	3,481	—
115	—	llama-13bOpenMeta	868	±12	2,446	—
116	—	stablelm-tuned-alpha-7bOpenStability AI	859	±10	3,339	—

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