Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	llama-3.1-405b-instruct-fp8OpenMeta	1,252	±3	63,247	—
2	—	llama-3.1-405b-instruct-bf16OpenMeta	1,252	±5	14,927	—
3	—	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,239	±6	6,417	—
4	—	llama-3.3-70b-instructOpenMeta	1,234	±7	8,907	—
5	—	athene-v2-chatOpenNexusFlow	1,232	±6	14,536	—
6	—	mistral-large-2407OpenMistral · 1 more variant	1,231	±3	48,365	—
7	—	qwen-max-0919OpenAlibaba	1,231	±5	17,577	—
8	—	athene-70b-0725OpenNexusFlow	1,223	±4	20,648	—
9	—	qwen2.5-72b-instructOpenAlibaba	1,222	±4	36,753	—
10	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,216	±7	7,667	—
11	—	llama-3.1-70b-instructOpenMeta	1,214	±4	58,794	—
12	—	gemma-2-27b-itOpenGoogle	1,207	±3	69,149	—
13	—	jamba-1.5-largeOpenAI21 Labs	1,205	±6	9,141	—
14	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,204	±8	3,926	—
15	—	gemma-2-9b-it-simpoOpenPrinceton	1,199	±5	10,567	—
16	—	command-r-plus-08-2024OpenCohere	1,197	±6	10,574	—
17	—	nemotron-4-340b-instructOpenNVIDIA	1,196	±4	20,649	—
18	—	llama-3-70b-instructOpenMeta	1,195	±2	163,878	—
19	—	qwen2.5-coder-32b-instructOpenAlibaba	1,189	±9	5,748	—
20	—	c4ai-aya-expanse-32bOpenCohere	1,184	±4	23,536	—
21	—	command-r-plusOpenCohere	1,183	±3	80,916	—
22	—	deepseek-coder-v2OpenDeepSeek	1,182	±4	15,784	—
23	—	qwen2-72b-instructOpenAlibaba	1,181	±4	38,963	—
24	—	gemma-2-9b-itOpenGoogle	1,179	±4	46,948	—
25	—	command-r-08-2024OpenCohere	1,176	±6	10,873	—
26	—	jamba-1.5-miniOpenAI21 Labs	1,160	±8	9,278	—
27	—	ministral-8b-2410OpenMistral	1,160	±7	5,144	—
28	—	qwen1.5-110b-chatOpenAlibaba	1,155	±3	27,458	—
29	—	c4ai-aya-expanse-8bOpenCohere	1,151	±7	5,426	—
30	—	mixtral-8x22b-instruct-v0.1OpenMistral	1,149	±3	53,823	—
31	—	qwen1.5-72b-chatOpenAlibaba	1,148	±3	40,641	—
32	—	command-rOpenCohere	1,148	±3	56,399	—
33	—	llama-3-8b-instructOpenMeta	1,143	±3	109,267	—
34	—	yi-1.5-34b-chatOpen01 AI	1,133	±4	25,152	—
35	—	llama-3.1-8b-instructOpenMeta	1,133	±3	52,712	—
36	—	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,130	±8	4,862	—
37	—	qwen1.5-32b-chatOpenAlibaba	1,127	±4	22,762	—
38	—	phi-3-medium-4k-instructOpenMicrosoft	1,118	±4	26,122	—
39	—	internlm2_5-20b-chatOpenInternLM	1,116	±7	10,679	—
40	—	gemma-2-2b-itOpenGoogle	1,116	±4	38,514	—
41	—	mixtral-8x7b-instruct-v0.1OpenMistral	1,114	±0	76,152	—
42	—	dbrx-instruct-previewOpenDatabricks	1,113	±3	33,738	—
43	—	granite-3.0-8b-instructOpenIBM	1,110	±8	7,068	—
44	—	qwen1.5-14b-chatOpenAlibaba	1,107	±5	18,678	—
45	—	wizardlm-70bOpenMicrosoft	1,105	±7	8,381	—
46	—	snowflake-arctic-instructOpenSnowflake	1,102	±3	34,181	—
47	—	yi-34b-chatOpen01 AI	1,101	±6	15,932	—
48	—	openchat-3.5-0106OpenOpenChat · 1 more variant	1,100	±6	12,985	—
49	—	gemma-1.1-7b-itOpenGoogle	1,099	±4	25,072	—
50	—	phi-3-small-8k-instructOpenMicrosoft	1,098	±4	18,503	—
51	—	llama-3.2-3b-instructOpenMeta	1,094	±7	8,423	—
52	—	tulu-2-dpo-70bOpenAllenAI/UW	1,092	±7	6,662	—
53	—	starling-lm-7b-betaOpenNexusflow	1,092	±4	16,671	—
54	—	vicuna-33bOpenLMSYS	1,091	±4	22,953	—
55	—	deepseek-llm-67b-chatOpenDeepSeek	1,091	±8	4,985	—
56	—	openhermes-2.5-mistral-7bOpenNousResearch	1,090	±8	5,089	—
57	—	qwq-32b-previewOpenAlibaba	1,087	±10	3,294	—
58	—	starling-lm-7b-alphaOpenUC Berkeley	1,083	±6	10,415	—
59	—	granite-3.0-2b-instructOpenIBM	1,082	±8	7,240	—
60	—	llama-2-70b-chatOpenMeta	1,082	±3	39,638	—
61	—	llama2-70b-steerlm-chatOpenNVIDIA	1,074	±9	3,637	—
62	—	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,072	±8	3,835	—
63	—	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,069	±13	1,713	—
64	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,068	±6	12,853	—
65	—	mistral-7b-instruct-v0.2OpenMistral	1,067	±4	20,066	—
66	—	solar-10.7b-instruct-v1.0OpenUpstage AI	1,066	±9	4,289	—
67	—	qwen1.5-7b-chatOpenAlibaba	1,065	±8	4,866	—
68	—	wizardlm-13bOpenMicrosoft	1,063	±7	7,182	—
69	—	mpt-30b-chatOpenMosaicML	1,060	±10	2,648	—
70	—	falcon-180b-chatOpenTII	1,059	±14	1,327	—
71	—	vicuna-13bOpenLMSYS	1,058	±5	19,792	—
72	—	qwen-14b-chatOpenAlibaba	1,056	±8	5,072	—
73	—	phi-3-mini-4k-instructOpenMicrosoft	1,056	±4	21,097	—
74	—	llama-2-13b-chatOpenMeta	1,054	±5	19,748	—
75	—	zephyr-7b-betaOpenHuggingFace	1,049	±6	11,333	—
76	—	phi-3-mini-128k-instructOpenMicrosoft	1,048	±4	21,636	—
77	—	gemma-7b-itOpenGoogle	1,048	±7	9,179	—
78	—	codellama-34b-instructOpenMeta	1,047	±7	7,514	—
79	—	zephyr-7b-alphaOpenHuggingFace	1,046	±13	1,814	—
80	—	llama-3.2-1b-instructOpenMeta	1,045	±6	8,548	—
81	—	gemma-1.1-2b-itOpenGoogle	1,040	±7	11,353	—
82	—	guanaco-33bOpenUW	1,040	±10	2,999	—
83	—	codellama-70b-instructOpenMeta	1,038	±15	1,191	—
84	—	stripedhyena-nous-7bOpenTogether AI	1,034	±7	5,269	—
85	—	mistral-7b-instructOpenMistral	1,027	±6	9,143	—
86	—	llama-2-7b-chatOpenMeta	1,025	±4	14,550	—
87	—	vicuna-7bOpenLMSYS	1,022	±8	7,014	—
88	—	qwen1.5-4b-chatOpenAlibaba	1,015	±7	7,812	—
89	—	gemma-2b-itOpenGoogle	1,008	±8	4,922	—
90	—	olmo-7b-instructOpenAi2	994	±8	6,505	—
91	—	koala-13bOpenUC Berkeley	980	±7	7,036	—
92	—	chatglm3-6bOpenTsinghua	974	±10	4,763	—
93	—	gpt4all-13b-snoozyOpenNomic AI	972	±14	1,787	—
94	—	alpaca-13bOpenStanford	967	±8	5,874	—
95	—	mpt-7b-chatOpenMosaicML	967	±9	4,013	—
96	—	RWKV-4-Raven-14BOpenRWKV	949	±10	4,934	—
97	—	chatglm2-6bOpenTsinghua	942	±10	2,709	—
98	—	oasst-pythia-12bOpenOpenAssistant	931	±9	6,380	—
99	—	fastchat-t5-3bOpenLMSYS	896	±9	4,301	—
100	—	chatglm-6bOpenTsinghua	888	±10	4,991	—
101	—	dolly-v2-12bOpenDatabricks	881	±11	3,486	—
102	—	llama-13bOpenMeta	867	±13	2,444	—
103	—	stablelm-tuned-alpha-7bOpenStability AI	859	±10	3,341	—

53 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