Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	New	deepseek-v3OpenDeepSeek	1,278	±7	6,639	—
2	▼ 1	llama-3.1-405b-instruct-fp8OpenMeta	1,253	±3	63,222	—
3	▼ 1	llama-3.1-405b-instruct-bf16OpenMeta	1,253	±4	18,184	—
4	▼ 1	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,240	±7	7,271	—
5	▼ 1	llama-3.3-70b-instructOpenMeta	1,235	±5	12,451	—
6	▼ 1	athene-v2-chatOpenNexusFlow	1,232	±5	18,033	—
7	▼ 1	mistral-large-2407OpenMistral · 1 more variant	1,232	±3	48,205	—
8	▼ 1	qwen-max-0919OpenAlibaba	1,231	±5	17,436	—
9	▼ 1	athene-70b-0725OpenNexusFlow	1,223	±3	20,624	—
10	▼ 1	qwen2.5-72b-instructOpenAlibaba	1,223	±3	38,466	—
11	▼ 1	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,217	±6	7,603	—
12	▼ 1	llama-3.1-70b-instructOpenMeta	1,214	±3	58,806	—
13	New	llama-3.1-tulu-3-70bOpenAi2	1,211	±11	2,054	—
14	▼ 2	gemma-2-27b-itOpenGoogle	1,207	±3	70,811	—
15	▼ 2	jamba-1.5-largeOpenAI21 Labs	1,205	±6	9,127	—
16	▼ 2	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,204	±9	3,897	—
17	▼ 2	gemma-2-9b-it-simpoOpenPrinceton	1,200	±6	10,555	—
18	▼ 2	command-r-plus-08-2024OpenCohere	1,197	±6	10,553	—
19	▼ 2	nemotron-4-340b-instructOpenNVIDIA	1,196	±4	20,615	—
20	▼ 2	llama-3-70b-instructOpenMeta	1,195	±2	163,781	—
21	▼ 2	qwen2.5-coder-32b-instructOpenAlibaba	1,190	±7	5,725	—
22	▼ 2	c4ai-aya-expanse-32bOpenCohere	1,185	±4	25,444	—
23	▼ 2	command-r-plusOpenCohere	1,183	±2	80,863	—
24	▼ 2	deepseek-coder-v2OpenDeepSeek	1,182	±4	15,752	—
25	▼ 2	qwen2-72b-instructOpenAlibaba	1,181	±3	38,884	—
26	▼ 2	gemma-2-9b-itOpenGoogle	1,179	±3	48,642	—
27	▼ 2	command-r-08-2024OpenCohere	1,176	±6	10,845	—
28	▼ 2	jamba-1.5-miniOpenAI21 Labs	1,160	±6	9,263	—
29	▼ 2	ministral-8b-2410OpenMistral	1,160	±8	5,115	—
30	▼ 2	qwen1.5-110b-chatOpenAlibaba	1,156	±4	27,470	—
31	▼ 2	c4ai-aya-expanse-8bOpenCohere	1,152	±6	7,159	—
32	New	llama-3.1-tulu-3-8bOpenAi2	1,150	±12	2,040	—
33	▼ 3	mixtral-8x22b-instruct-v0.1OpenMistral	1,149	±3	53,792	—
34	▼ 3	qwen1.5-72b-chatOpenAlibaba	1,148	±3	40,634	—
35	▼ 3	command-rOpenCohere	1,148	±3	56,382	—
36	▼ 3	llama-3-8b-instructOpenMeta	1,143	±3	109,217	—
37	▼ 3	yi-1.5-34b-chatOpen01 AI	1,133	±3	25,129	—
38	▼ 3	llama-3.1-8b-instructOpenMeta	1,133	±3	52,649	—
39	▼ 3	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,131	±9	4,860	—
40	▼ 3	qwen1.5-32b-chatOpenAlibaba	1,127	±4	22,769	—
41	▼ 3	phi-3-medium-4k-instructOpenMicrosoft	1,118	±4	26,106	—
42	▼ 3	internlm2_5-20b-chatOpenInternLM	1,116	±5	10,596	—
43	▼ 3	gemma-2-2b-itOpenGoogle	1,116	±3	40,232	—
44	▼ 3	mixtral-8x7b-instruct-v0.1OpenMistral	1,114	±0	76,131	—
45	▼ 3	dbrx-instruct-previewOpenDatabricks	1,113	±3	33,731	—
46	▼ 3	granite-3.0-8b-instructOpenIBM	1,110	±7	7,003	—
47	▼ 3	qwen1.5-14b-chatOpenAlibaba	1,107	±4	18,679	—
48	▼ 3	wizardlm-70bOpenMicrosoft	1,105	±6	8,382	—
49	▼ 3	snowflake-arctic-instructOpenSnowflake	1,103	±4	34,181	—
50	▼ 3	yi-34b-chatOpen01 AI	1,101	±4	15,928	—
51	▼ 3	openchat-3.5-0106OpenOpenChat · 1 more variant	1,100	±5	12,984	—
52	▼ 3	gemma-1.1-7b-itOpenGoogle	1,099	±4	25,062	—
53	▼ 3	phi-3-small-8k-instructOpenMicrosoft	1,098	±4	18,479	—
54	▼ 3	llama-3.2-3b-instructOpenMeta	1,094	±6	8,413	—
55	▼ 3	tulu-2-dpo-70bOpenAllenAI/UW	1,092	±8	6,662	—
56	▼ 3	starling-lm-7b-betaOpenNexusflow	1,092	±4	16,670	—
57	▼ 3	vicuna-33bOpenLMSYS	1,092	±4	22,952	—
58	▼ 3	deepseek-llm-67b-chatOpenDeepSeek	1,091	±8	4,986	—
59	▼ 3	openhermes-2.5-mistral-7bOpenNousResearch	1,090	±9	5,087	—
60	▼ 3	qwq-32b-previewOpenAlibaba	1,089	±9	3,420	—
61	▼ 3	starling-lm-7b-alphaOpenUC Berkeley	1,083	±5	10,416	—
62	▼ 3	granite-3.0-2b-instructOpenIBM	1,082	±7	7,195	—
63	▼ 3	llama-2-70b-chatOpenMeta	1,082	±3	39,640	—
64	▼ 3	llama2-70b-steerlm-chatOpenNVIDIA	1,074	±8	3,637	—
65	▼ 3	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,072	±10	3,836	—
66	▼ 3	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,069	±13	1,713	—
67	▼ 3	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,068	±5	12,820	—
68	▼ 3	mistral-7b-instruct-v0.2OpenMistral	1,067	±4	20,054	—
69	▼ 3	solar-10.7b-instruct-v1.0OpenUpstage AI	1,066	±7	4,288	—
70	▼ 3	qwen1.5-7b-chatOpenAlibaba	1,065	±8	4,869	—
71	▼ 3	wizardlm-13bOpenMicrosoft	1,063	±7	7,180	—
72	▼ 3	mpt-30b-chatOpenMosaicML	1,060	±12	2,647	—
73	▼ 3	falcon-180b-chatOpenTII	1,059	±15	1,328	—
74	▼ 3	vicuna-13bOpenLMSYS	1,058	±4	19,788	—
75	▼ 3	qwen-14b-chatOpenAlibaba	1,057	±8	5,070	—
76	▼ 3	phi-3-mini-4k-instructOpenMicrosoft	1,056	±4	21,090	—
77	▼ 3	llama-2-13b-chatOpenMeta	1,054	±4	19,741	—
78	New	smollm2-1.7b-instructOpenHuggingFace	1,052	±12	2,379	—
79	▼ 4	zephyr-7b-betaOpenHuggingFace	1,049	±5	11,331	—
80	▼ 4	phi-3-mini-128k-instructOpenMicrosoft	1,049	±4	21,620	—
81	▼ 4	gemma-7b-itOpenGoogle	1,048	±6	9,177	—
82	▼ 4	codellama-34b-instructOpenMeta	1,047	±7	7,511	—
83	▼ 4	zephyr-7b-alphaOpenHuggingFace	1,046	±13	1,812	—
84	▼ 4	llama-3.2-1b-instructOpenMeta	1,045	±6	8,533	—
85	▼ 4	gemma-1.1-2b-itOpenGoogle	1,040	±5	11,352	—
86	▼ 4	guanaco-33bOpenUW	1,040	±12	2,999	—
87	▼ 4	codellama-70b-instructOpenMeta	1,038	±14	1,194	—
88	▼ 4	stripedhyena-nous-7bOpenTogether AI	1,034	±7	5,271	—
89	▼ 4	mistral-7b-instructOpenMistral	1,027	±6	9,145	—
90	▼ 4	llama-2-7b-chatOpenMeta	1,025	±5	14,548	—
91	▼ 4	vicuna-7bOpenLMSYS	1,022	±7	7,017	—
92	▼ 4	qwen1.5-4b-chatOpenAlibaba	1,015	±7	7,811	—
93	▼ 4	gemma-2b-itOpenGoogle	1,008	±10	4,919	—
94	▼ 4	olmo-7b-instructOpenAi2	994	±7	6,507	—
95	▼ 4	koala-13bOpenUC Berkeley	979	±7	7,035	—
96	▼ 4	chatglm3-6bOpenTsinghua	975	±9	4,762	—
97	▼ 4	gpt4all-13b-snoozyOpenNomic AI	972	±17	1,786	—
98	▼ 4	alpaca-13bOpenStanford	967	±9	5,876	—
99	▼ 4	mpt-7b-chatOpenMosaicML	967	±12	4,012	—
100	▼ 4	RWKV-4-Raven-14BOpenRWKV	949	±11	4,934	—
101	▼ 4	chatglm2-6bOpenTsinghua	942	±11	2,708	—
102	▼ 4	oasst-pythia-12bOpenOpenAssistant	931	±8	6,381	—
103	▼ 4	fastchat-t5-3bOpenLMSYS	896	±9	4,301	—
104	▼ 4	chatglm-6bOpenTsinghua	888	±11	4,990	—
105	▼ 4	dolly-v2-12bOpenDatabricks	881	±9	3,485	—
106	▼ 4	llama-13bOpenMeta	867	±12	2,445	—
107	▼ 4	stablelm-tuned-alpha-7bOpenStability AI	859	±9	3,341	—

57 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