Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	deepseek-r1OpenDeepSeek	1,320	±7	8,099	—
2	—	deepseek-v3OpenDeepSeek	1,277	±4	21,425	—
3	—	llama-3.1-405b-instruct-bf16OpenMeta	1,254	±4	33,602	—
4	—	llama-3.1-405b-instruct-fp8OpenMeta	1,253	±3	63,130	—
5	—	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,240	±8	7,250	—
6	—	llama-3.3-70b-instructOpenMeta	1,235	±4	27,913	—
7	—	mistral-large-2407OpenMistral · 1 more variant	1,232	±3	48,181	—
8	—	qwen-max-0919OpenAlibaba	1,231	±5	17,427	—
9	—	athene-v2-chatOpenNexusFlow	1,231	±4	26,092	—
10	—	athene-70b-0725OpenNexusFlow	1,223	±4	20,601	—
11	—	qwen2.5-72b-instructOpenAlibaba	1,222	±4	41,527	—
12	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,216	±8	7,599	—
13	—	llama-3.1-70b-instructOpenMeta	1,214	±3	58,740	—
14	—	llama-3.1-tulu-3-70bOpenAi2	1,209	±12	3,009	—
15	—	gemma-2-27b-itOpenGoogle	1,207	±3	78,600	—
16	—	jamba-1.5-largeOpenAI21 Labs	1,205	±5	9,122	—
17	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,204	±9	3,890	—
18	—	gemma-2-9b-it-simpoOpenPrinceton	1,200	±5	10,552	—
19	—	command-r-plus-08-2024OpenCohere	1,197	±5	10,538	—
20	—	nemotron-4-340b-instructOpenNVIDIA	1,196	±4	20,611	—
21	—	llama-3-70b-instructOpenMeta	1,195	±3	163,722	—
22	—	qwen2.5-coder-32b-instructOpenAlibaba	1,190	±6	5,730	—
23	—	c4ai-aya-expanse-32bOpenCohere	1,185	±4	28,749	—
24	—	mistral-small-24b-instruct-2501OpenMistral	1,185	±7	8,425	—
25	—	command-r-plusOpenCohere	1,183	±3	80,857	—
26	—	deepseek-coder-v2OpenDeepSeek	1,182	±4	15,754	—
27	—	qwen2-72b-instructOpenAlibaba	1,181	±4	38,866	—
28	—	gemma-2-9b-itOpenGoogle	1,180	±3	56,248	—
29	▲ 1	command-r-08-2024OpenCohere	1,176	±5	10,835	—
30	▼ 1	phi-4OpenMicrosoft	1,175	±5	15,223	—
31	—	jamba-1.5-miniOpenAI21 Labs	1,160	±6	9,267	—
32	—	ministral-8b-2410OpenMistral	1,160	±8	5,112	—
33	—	qwen1.5-110b-chatOpenAlibaba	1,155	±4	27,451	—
34	—	c4ai-aya-expanse-8bOpenCohere	1,151	±6	10,400	—
35	—	mixtral-8x22b-instruct-v0.1OpenMistral	1,149	±3	53,767	—
36	—	qwen1.5-72b-chatOpenAlibaba	1,148	±3	40,635	—
37	—	command-rOpenCohere	1,148	±4	56,362	—
38	—	llama-3.1-tulu-3-8bOpenAi2	1,147	±9	3,072	—
39	—	llama-3-8b-instructOpenMeta	1,143	±3	109,221	—
40	—	granite-3.1-8b-instructOpenIBM	1,134	±11	3,298	—
41	—	yi-1.5-34b-chatOpen01 AI	1,133	±4	25,124	—
42	—	llama-3.1-8b-instructOpenMeta	1,133	±3	52,632	—
43	—	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,130	±8	4,859	—
44	—	qwen1.5-32b-chatOpenAlibaba	1,126	±3	22,751	—
45	—	phi-3-medium-4k-instructOpenMicrosoft	1,118	±4	26,090	—
46	—	gemma-2-2b-itOpenGoogle	1,117	±3	47,976	—
47	—	internlm2_5-20b-chatOpenInternLM	1,116	±5	10,595	—
48	—	mixtral-8x7b-instruct-v0.1OpenMistral	1,114	±0	76,093	—
49	—	dbrx-instruct-previewOpenDatabricks	1,113	±3	33,713	—
50	—	granite-3.0-8b-instructOpenIBM	1,110	±7	6,999	—
51	—	qwen1.5-14b-chatOpenAlibaba	1,107	±4	18,669	—
52	—	wizardlm-70bOpenMicrosoft	1,105	±7	8,380	—
53	—	granite-3.1-2b-instructOpenIBM	1,104	±9	3,382	—
54	—	snowflake-arctic-instructOpenSnowflake	1,102	±4	34,174	—
55	—	yi-34b-chatOpen01 AI	1,101	±5	15,922	—
56	—	openchat-3.5-0106OpenOpenChat · 1 more variant	1,100	±5	12,976	—
57	—	gemma-1.1-7b-itOpenGoogle	1,099	±4	25,061	—
58	—	phi-3-small-8k-instructOpenMicrosoft	1,098	±5	18,478	—
59	—	llama-3.2-3b-instructOpenMeta	1,093	±6	8,403	—
60	—	tulu-2-dpo-70bOpenAllenAI/UW	1,092	±7	6,657	—
61	—	starling-lm-7b-betaOpenNexusflow	1,092	±4	16,669	—
62	—	vicuna-33bOpenLMSYS	1,091	±5	22,943	—
63	—	deepseek-llm-67b-chatOpenDeepSeek	1,091	±8	4,985	—
64	—	openhermes-2.5-mistral-7bOpenNousResearch	1,089	±7	5,086	—
65	—	qwq-32b-previewOpenAlibaba	1,088	±9	3,417	—
66	—	starling-lm-7b-alphaOpenUC Berkeley	1,083	±6	10,413	—
67	▲ 1	granite-3.0-2b-instructOpenIBM	1,082	±7	7,187	—
68	▼ 1	llama-2-70b-chatOpenMeta	1,082	±3	39,619	—
69	—	llama2-70b-steerlm-chatOpenNVIDIA	1,074	±8	3,637	—
70	—	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,072	±9	3,833	—
71	—	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,069	±14	1,712	—
72	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,068	±6	12,808	—
73	—	mistral-7b-instruct-v0.2OpenMistral	1,067	±4	20,050	—
74	—	solar-10.7b-instruct-v1.0OpenUpstage AI	1,066	±9	4,289	—
75	—	qwen1.5-7b-chatOpenAlibaba	1,065	±9	4,864	—
76	—	wizardlm-13bOpenMicrosoft	1,063	±7	7,175	—
77	—	mpt-30b-chatOpenMosaicML	1,059	±9	2,646	—
78	—	falcon-180b-chatOpenTII	1,059	±16	1,328	—
79	—	vicuna-13bOpenLMSYS	1,058	±4	19,776	—
80	—	qwen-14b-chatOpenAlibaba	1,056	±7	5,066	—
81	—	phi-3-mini-4k-instructOpenMicrosoft	1,056	±5	21,088	—
82	—	llama-2-13b-chatOpenMeta	1,054	±4	19,731	—
83	—	smollm2-1.7b-instructOpenHuggingFace	1,050	±13	2,369	—
84	—	zephyr-7b-betaOpenHuggingFace	1,049	±6	11,325	—
85	—	phi-3-mini-128k-instructOpenMicrosoft	1,049	±4	21,617	—
86	—	gemma-7b-itOpenGoogle	1,048	±6	9,181	—
87	—	codellama-34b-instructOpenMeta	1,047	±7	7,509	—
88	—	zephyr-7b-alphaOpenHuggingFace	1,046	±12	1,814	—
89	—	llama-3.2-1b-instructOpenMeta	1,045	±8	8,529	—
90	—	gemma-1.1-2b-itOpenGoogle	1,041	±6	11,351	—
91	—	guanaco-33bOpenUW	1,039	±12	2,995	—
92	—	codellama-70b-instructOpenMeta	1,039	±15	1,192	—
93	—	stripedhyena-nous-7bOpenTogether AI	1,034	±8	5,272	—
94	—	mistral-7b-instructOpenMistral	1,026	±7	9,142	—
95	—	llama-2-7b-chatOpenMeta	1,024	±5	14,550	—
96	—	vicuna-7bOpenLMSYS	1,021	±8	7,015	—
97	—	qwen1.5-4b-chatOpenAlibaba	1,014	±7	7,816	—
98	—	gemma-2b-itOpenGoogle	1,008	±7	4,920	—
99	—	olmo-7b-instructOpenAi2	994	±7	6,501	—
100	—	koala-13bOpenUC Berkeley	980	±7	7,024	—
101	—	chatglm3-6bOpenTsinghua	974	±8	4,761	—
102	—	gpt4all-13b-snoozyOpenNomic AI	973	±16	1,787	—
103	—	mpt-7b-chatOpenMosaicML	967	±10	3,997	—
104	—	alpaca-13bOpenStanford	967	±8	5,866	—
105	—	RWKV-4-Raven-14BOpenRWKV	949	±8	4,919	—
106	—	chatglm2-6bOpenTsinghua	942	±12	2,707	—
107	—	oasst-pythia-12bOpenOpenAssistant	931	±8	6,370	—
108	—	fastchat-t5-3bOpenLMSYS	896	±10	4,287	—
109	—	chatglm-6bOpenTsinghua	888	±11	4,979	—
110	—	dolly-v2-12bOpenDatabricks	881	±12	3,482	—
111	—	llama-13bOpenMeta	867	±10	2,444	—
112	—	stablelm-tuned-alpha-7bOpenStability AI	859	±10	3,334	—

62 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