Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	deepseek-v3-0324OpenDeepSeek · 1 more variant	1,319	±9	3,526	—
2	—	deepseek-r1OpenDeepSeek	1,315	±5	14,259	—
3	—	gemma-3-27b-itOpenGoogle	1,280	±7	8,420	—
4	—	command-a-03-2025OpenCohere	1,265	±9	5,156	—
5	—	qwq-32bOpenAlibaba · 1 more variant	1,257	±7	5,662	—
6	—	llama-3.1-405b-instruct-bf16OpenMeta	1,253	±3	41,531	—
7	—	llama-3.1-405b-instruct-fp8OpenMeta	1,252	±3	63,065	—
8	—	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,246	±11	2,374	—
9	—	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,239	±6	7,252	—
10	—	llama-3.3-70b-instructOpenMeta	1,235	±4	35,912	—
11	—	mistral-large-2407OpenMistral · 1 more variant	1,231	±3	48,227	—
12	—	qwen-max-0919OpenAlibaba	1,231	±4	17,433	—
13	—	athene-v2-chatOpenNexusFlow	1,230	±4	26,106	—
14	—	athene-70b-0725OpenNexusFlow	1,223	±4	20,594	—
15	—	qwen2.5-72b-instructOpenAlibaba	1,222	±3	41,525	—
16	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,216	±7	7,575	—
17	—	llama-3.1-70b-instructOpenMeta	1,213	±3	58,667	—
18	—	llama-3.1-tulu-3-70bOpenAi2	1,208	±9	3,014	—
19	—	gemma-2-27b-itOpenGoogle	1,207	±3	79,545	—
20	—	jamba-1.5-largeOpenAI21 Labs	1,205	±6	9,131	—
21	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,203	±8	3,886	—
22	—	gemma-2-9b-it-simpoOpenPrinceton	1,199	±6	10,553	—
23	—	command-r-plus-08-2024OpenCohere	1,197	±6	10,542	—
24	—	nemotron-4-340b-instructOpenNVIDIA	1,196	±5	20,609	—
25	—	llama-3-70b-instructOpenMeta	1,195	±2	163,676	—
26	—	qwen2.5-coder-32b-instructOpenAlibaba	1,189	±8	5,731	—
27	—	mistral-small-24b-instruct-2501OpenMistral	1,188	±6	13,327	—
28	—	c4ai-aya-expanse-32bOpenCohere	1,185	±3	28,757	—
29	—	command-r-plusOpenCohere	1,183	±2	80,845	—
30	—	deepseek-coder-v2OpenDeepSeek	1,182	±4	15,753	—
31	—	qwen2-72b-instructOpenAlibaba	1,181	±3	38,891	—
32	—	gemma-2-9b-itOpenGoogle	1,180	±3	57,207	—
33	▲ 1	phi-4OpenMicrosoft	1,176	±5	23,391	—
34	▼ 1	command-r-08-2024OpenCohere	1,175	±5	10,848	—
35	—	jamba-1.5-miniOpenAI21 Labs	1,160	±5	9,269	—
36	—	ministral-8b-2410OpenMistral	1,160	±9	5,115	—
37	—	qwen1.5-110b-chatOpenAlibaba	1,155	±3	27,440	—
38	—	c4ai-aya-expanse-8bOpenCohere	1,151	±6	10,391	—
39	—	mixtral-8x22b-instruct-v0.1OpenMistral	1,149	±3	53,776	—
40	—	qwen1.5-72b-chatOpenAlibaba	1,148	±3	40,666	—
41	—	command-rOpenCohere	1,148	±3	56,383	—
42	—	llama-3.1-tulu-3-8bOpenAi2	1,147	±11	3,074	—
43	—	llama-3-8b-instructOpenMeta	1,142	±3	109,087	—
44	—	granite-3.1-8b-instructOpenIBM	1,134	±9	3,295	—
45	—	yi-1.5-34b-chatOpen01 AI	1,133	±4	25,138	—
46	—	llama-3.1-8b-instructOpenMeta	1,132	±3	52,610	—
47	—	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,130	±6	4,861	—
48	—	qwen1.5-32b-chatOpenAlibaba	1,126	±4	22,772	—
49	—	phi-3-medium-4k-instructOpenMicrosoft	1,118	±4	26,113	—
50	—	gemma-2-2b-itOpenGoogle	1,117	±4	48,898	—
51	—	internlm2_5-20b-chatOpenInternLM	1,116	±5	10,593	—
52	—	mixtral-8x7b-instruct-v0.1OpenMistral	1,114	±0	76,132	—
53	—	dbrx-instruct-previewOpenDatabricks	1,113	±4	33,747	—
54	—	granite-3.0-8b-instructOpenIBM	1,110	±9	7,000	—
55	—	qwen1.5-14b-chatOpenAlibaba	1,107	±4	18,695	—
56	—	wizardlm-70bOpenMicrosoft	1,105	±6	8,383	—
57	—	granite-3.1-2b-instructOpenIBM	1,104	±10	3,381	—
58	—	snowflake-arctic-instructOpenSnowflake	1,102	±4	34,178	—
59	—	yi-34b-chatOpen01 AI	1,101	±5	15,923	—
60	—	openchat-3.5-0106OpenOpenChat · 1 more variant	1,100	±4	12,990	—
61	—	gemma-1.1-7b-itOpenGoogle	1,099	±4	25,078	—
62	—	phi-3-small-8k-instructOpenMicrosoft	1,098	±4	18,472	—
63	—	llama-3.2-3b-instructOpenMeta	1,093	±6	8,396	—
64	—	tulu-2-dpo-70bOpenAllenAI/UW	1,092	±7	6,659	—
65	—	starling-lm-7b-betaOpenNexusflow	1,092	±5	16,676	—
66	—	vicuna-33bOpenLMSYS	1,092	±4	22,946	—
67	—	deepseek-llm-67b-chatOpenDeepSeek	1,091	±8	4,987	—
68	—	openhermes-2.5-mistral-7bOpenNousResearch	1,090	±7	5,088	—
69	—	starling-lm-7b-alphaOpenUC Berkeley	1,083	±5	10,416	—
70	—	granite-3.0-2b-instructOpenIBM	1,082	±6	7,185	—
71	—	llama-2-70b-chatOpenMeta	1,082	±3	39,610	—
72	—	llama2-70b-steerlm-chatOpenNVIDIA	1,074	±10	3,635	—
73	—	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,072	±9	3,839	—
74	—	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,070	±12	1,712	—
75	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,067	±5	12,809	—
76	—	mistral-7b-instruct-v0.2OpenMistral	1,067	±4	20,068	—
77	—	solar-10.7b-instruct-v1.0OpenUpstage AI	1,066	±8	4,287	—
78	—	qwen1.5-7b-chatOpenAlibaba	1,065	±8	4,872	—
79	—	wizardlm-13bOpenMicrosoft	1,064	±7	7,175	—
80	—	mpt-30b-chatOpenMosaicML	1,060	±11	2,645	—
81	—	falcon-180b-chatOpenTII	1,060	±18	1,328	—
82	—	vicuna-13bOpenLMSYS	1,059	±4	19,772	—
83	—	qwen-14b-chatOpenAlibaba	1,056	±8	5,068	—
84	—	phi-3-mini-4k-instructOpenMicrosoft	1,056	±4	21,099	—
85	—	llama-2-13b-chatOpenMeta	1,054	±4	19,726	—
86	—	smollm2-1.7b-instructOpenHuggingFace	1,050	±13	2,377	—
87	—	zephyr-7b-betaOpenHuggingFace	1,049	±6	11,322	—
88	—	phi-3-mini-128k-instructOpenMicrosoft	1,049	±4	21,639	—
89	—	gemma-7b-itOpenGoogle	1,048	±6	9,174	—
90	—	codellama-34b-instructOpenMeta	1,047	±7	7,511	—
91	—	zephyr-7b-alphaOpenHuggingFace	1,046	±13	1,813	—
92	—	llama-3.2-1b-instructOpenMeta	1,044	±6	8,518	—
93	—	gemma-1.1-2b-itOpenGoogle	1,040	±6	11,346	—
94	—	guanaco-33bOpenUW	1,040	±11	3,000	—
95	—	codellama-70b-instructOpenMeta	1,039	±17	1,192	—
96	—	stripedhyena-nous-7bOpenTogether AI	1,034	±8	5,277	—
97	—	mistral-7b-instructOpenMistral	1,026	±6	9,143	—
98	—	llama-2-7b-chatOpenMeta	1,025	±4	14,533	—
99	—	vicuna-7bOpenLMSYS	1,022	±7	7,014	—
100	—	qwen1.5-4b-chatOpenAlibaba	1,015	±6	7,820	—
101	—	gemma-2b-itOpenGoogle	1,008	±8	4,920	—
102	—	olmo-7b-instructOpenAi2	994	±6	6,504	—
103	—	koala-13bOpenUC Berkeley	981	±6	7,021	—
104	—	chatglm3-6bOpenTsinghua	974	±9	4,762	—
105	—	gpt4all-13b-snoozyOpenNomic AI	974	±14	1,788	—
106	—	mpt-7b-chatOpenMosaicML	968	±8	3,997	—
107	—	alpaca-13bOpenStanford	968	±7	5,864	—
108	—	RWKV-4-Raven-14BOpenRWKV	950	±10	4,920	—
109	—	chatglm2-6bOpenTsinghua	943	±10	2,711	—
110	—	oasst-pythia-12bOpenOpenAssistant	932	±8	6,370	—
111	—	fastchat-t5-3bOpenLMSYS	897	±10	4,287	—
112	—	chatglm-6bOpenTsinghua	889	±10	4,983	—
113	—	dolly-v2-12bOpenDatabricks	883	±10	3,481	—
114	—	llama-13bOpenMeta	869	±12	2,445	—
115	—	stablelm-tuned-alpha-7bOpenStability AI	860	±11	3,336	—

65 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