Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	deepseek-v3OpenDeepSeek	1,279	±5	11,591	—
2	▲ 1	llama-3.1-405b-instruct-bf16OpenMeta	1,254	±5	21,285	—
3	▼ 1	llama-3.1-405b-instruct-fp8OpenMeta	1,253	±3	63,202	—
4	—	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,240	±6	7,261	—
5	—	llama-3.3-70b-instructOpenMeta	1,235	±4	15,516	—
6	—	athene-v2-chatOpenNexusFlow	1,232	±4	21,014	—
7	—	mistral-large-2407OpenMistral · 1 more variant	1,232	±3	48,207	—
8	—	qwen-max-0919OpenAlibaba	1,231	±5	17,436	—
9	—	athene-70b-0725OpenNexusFlow	1,223	±4	20,618	—
10	—	qwen2.5-72b-instructOpenAlibaba	1,223	±4	39,984	—
11	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,217	±6	7,596	—
12	—	llama-3.1-70b-instructOpenMeta	1,214	±3	58,786	—
13	—	llama-3.1-tulu-3-70bOpenAi2	1,210	±10	3,026	—
14	—	gemma-2-27b-itOpenGoogle	1,208	±3	72,425	—
15	—	jamba-1.5-largeOpenAI21 Labs	1,205	±7	9,125	—
16	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,204	±9	3,897	—
17	—	gemma-2-9b-it-simpoOpenPrinceton	1,200	±5	10,557	—
18	—	command-r-plus-08-2024OpenCohere	1,197	±6	10,546	—
19	—	nemotron-4-340b-instructOpenNVIDIA	1,196	±4	20,609	—
20	—	llama-3-70b-instructOpenMeta	1,195	±3	163,797	—
21	—	qwen2.5-coder-32b-instructOpenAlibaba	1,189	±8	5,731	—
22	—	c4ai-aya-expanse-32bOpenCohere	1,185	±4	26,994	—
23	—	command-r-plusOpenCohere	1,183	±3	80,868	—
24	New	phi-4OpenMicrosoft	1,182	±9	2,485	—
25	▼ 1	deepseek-coder-v2OpenDeepSeek	1,182	±5	15,752	—
26	▼ 1	qwen2-72b-instructOpenAlibaba	1,181	±4	38,889	—
27	▼ 1	gemma-2-9b-itOpenGoogle	1,179	±3	50,239	—
28	▼ 1	command-r-08-2024OpenCohere	1,176	±7	10,846	—
29	▼ 1	jamba-1.5-miniOpenAI21 Labs	1,160	±5	9,269	—
30	▼ 1	ministral-8b-2410OpenMistral	1,160	±7	5,109	—
31	▼ 1	qwen1.5-110b-chatOpenAlibaba	1,156	±3	27,467	—
32	▼ 1	c4ai-aya-expanse-8bOpenCohere	1,152	±6	8,797	—
33	—	mixtral-8x22b-instruct-v0.1OpenMistral	1,149	±3	53,788	—
34	—	qwen1.5-72b-chatOpenAlibaba	1,148	±3	40,638	—
35	—	command-rOpenCohere	1,148	±3	56,380	—
36	▼ 4	llama-3.1-tulu-3-8bOpenAi2	1,147	±10	3,077	—
37	▼ 1	llama-3-8b-instructOpenMeta	1,143	±3	109,211	—
38	▼ 1	yi-1.5-34b-chatOpen01 AI	1,133	±4	25,126	—
39	▼ 1	llama-3.1-8b-instructOpenMeta	1,133	±3	52,646	—
40	New	granite-3.1-8b-instructOpenIBM	1,131	±11	2,468	—
41	▼ 2	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,131	±8	4,860	—
42	▼ 2	qwen1.5-32b-chatOpenAlibaba	1,126	±4	22,772	—
43	▼ 2	phi-3-medium-4k-instructOpenMicrosoft	1,118	±4	26,112	—
44	▼ 1	gemma-2-2b-itOpenGoogle	1,116	±3	41,868	—
45	▼ 3	internlm2_5-20b-chatOpenInternLM	1,116	±5	10,599	—
46	▼ 2	mixtral-8x7b-instruct-v0.1OpenMistral	1,114	±0	76,138	—
47	▼ 2	dbrx-instruct-previewOpenDatabricks	1,113	±3	33,737	—
48	▼ 2	granite-3.0-8b-instructOpenIBM	1,109	±7	7,005	—
49	▼ 2	qwen1.5-14b-chatOpenAlibaba	1,107	±4	18,678	—
50	▼ 2	wizardlm-70bOpenMicrosoft	1,105	±7	8,380	—
51	▼ 2	snowflake-arctic-instructOpenSnowflake	1,102	±3	34,172	—
52	New	granite-3.1-2b-instructOpenIBM	1,102	±12	2,476	—
53	▼ 3	yi-34b-chatOpen01 AI	1,101	±5	15,922	—
54	▼ 3	openchat-3.5-0106OpenOpenChat · 1 more variant	1,100	±5	12,980	—
55	▼ 3	gemma-1.1-7b-itOpenGoogle	1,099	±4	25,065	—
56	▼ 3	phi-3-small-8k-instructOpenMicrosoft	1,098	±5	18,477	—
57	▼ 3	llama-3.2-3b-instructOpenMeta	1,094	±6	8,411	—
58	▼ 3	tulu-2-dpo-70bOpenAllenAI/UW	1,092	±6	6,663	—
59	▼ 3	starling-lm-7b-betaOpenNexusflow	1,092	±5	16,671	—
60	▼ 3	vicuna-33bOpenLMSYS	1,091	±4	22,950	—
61	▼ 3	deepseek-llm-67b-chatOpenDeepSeek	1,091	±8	4,987	—
62	▼ 3	openhermes-2.5-mistral-7bOpenNousResearch	1,090	±9	5,089	—
63	▼ 3	qwq-32b-previewOpenAlibaba	1,088	±8	3,415	—
64	▼ 3	starling-lm-7b-alphaOpenUC Berkeley	1,083	±5	10,416	—
65	▼ 3	granite-3.0-2b-instructOpenIBM	1,082	±8	7,193	—
66	▼ 3	llama-2-70b-chatOpenMeta	1,082	±3	39,634	—
67	▼ 3	llama2-70b-steerlm-chatOpenNVIDIA	1,074	±11	3,637	—
68	▼ 3	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,072	±9	3,835	—
69	▼ 2	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,068	±5	12,818	—
70	▼ 4	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,068	±12	1,713	—
71	▼ 3	mistral-7b-instruct-v0.2OpenMistral	1,067	±4	20,058	—
72	▼ 3	solar-10.7b-instruct-v1.0OpenUpstage AI	1,066	±9	4,288	—
73	▼ 3	qwen1.5-7b-chatOpenAlibaba	1,065	±7	4,868	—
74	▼ 3	wizardlm-13bOpenMicrosoft	1,063	±8	7,178	—
75	▼ 3	mpt-30b-chatOpenMosaicML	1,060	±11	2,648	—
76	▼ 3	falcon-180b-chatOpenTII	1,059	±12	1,327	—
77	▼ 3	vicuna-13bOpenLMSYS	1,059	±5	19,790	—
78	▼ 3	qwen-14b-chatOpenAlibaba	1,057	±9	5,070	—
79	▼ 3	phi-3-mini-4k-instructOpenMicrosoft	1,056	±4	21,085	—
80	▼ 3	llama-2-13b-chatOpenMeta	1,054	±4	19,738	—
81	▼ 3	smollm2-1.7b-instructOpenHuggingFace	1,051	±11	2,371	—
82	▼ 3	zephyr-7b-betaOpenHuggingFace	1,049	±5	11,334	—
83	▼ 3	phi-3-mini-128k-instructOpenMicrosoft	1,049	±4	21,632	—
84	▼ 3	gemma-7b-itOpenGoogle	1,048	±5	9,176	—
85	▼ 3	codellama-34b-instructOpenMeta	1,047	±7	7,515	—
86	▼ 3	zephyr-7b-alphaOpenHuggingFace	1,046	±16	1,814	—
87	▼ 3	llama-3.2-1b-instructOpenMeta	1,045	±6	8,535	—
88	▼ 3	gemma-1.1-2b-itOpenGoogle	1,040	±6	11,348	—
89	▼ 3	guanaco-33bOpenUW	1,040	±10	2,999	—
90	▼ 3	codellama-70b-instructOpenMeta	1,036	±16	1,194	—
91	▼ 3	stripedhyena-nous-7bOpenTogether AI	1,034	±8	5,273	—
92	▼ 3	mistral-7b-instructOpenMistral	1,027	±6	9,144	—
93	▼ 3	llama-2-7b-chatOpenMeta	1,025	±5	14,555	—
94	▼ 3	vicuna-7bOpenLMSYS	1,022	±7	7,015	—
95	▼ 3	qwen1.5-4b-chatOpenAlibaba	1,015	±6	7,813	—
96	▼ 3	gemma-2b-itOpenGoogle	1,008	±9	4,922	—
97	▼ 3	olmo-7b-instructOpenAi2	994	±8	6,504	—
98	▼ 3	koala-13bOpenUC Berkeley	980	±8	7,034	—
99	▼ 3	chatglm3-6bOpenTsinghua	974	±10	4,765	—
100	▼ 3	gpt4all-13b-snoozyOpenNomic AI	973	±15	1,786	—
101	▼ 2	mpt-7b-chatOpenMosaicML	967	±9	4,012	—
102	▼ 4	alpaca-13bOpenStanford	967	±7	5,876	—
103	▼ 3	RWKV-4-Raven-14BOpenRWKV	949	±9	4,934	—
104	▼ 3	chatglm2-6bOpenTsinghua	943	±11	2,707	—
105	▼ 3	oasst-pythia-12bOpenOpenAssistant	931	±9	6,380	—
106	▼ 3	fastchat-t5-3bOpenLMSYS	897	±8	4,302	—
107	▼ 3	chatglm-6bOpenTsinghua	889	±9	4,988	—
108	▼ 3	dolly-v2-12bOpenDatabricks	881	±11	3,485	—
109	▼ 3	llama-13bOpenMeta	868	±13	2,444	—
110	▼ 3	stablelm-tuned-alpha-7bOpenStability AI	859	±12	3,341	—

60 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