Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	▲ 1	llama-3.1-405b-instruct-fp8OpenMeta	1,250	±4	31,280	—
2	▼ 1	llama-3.1-405b-instruct-bf16OpenMeta	1,249	±7	5,865	—
3	—	mistral-large-2407OpenMistral	1,228	±4	27,285	—
4	—	athene-70b-0725OpenNexusFlow	1,218	±4	20,738	—
5	—	deepseek-v2.5OpenDeepSeek	1,211	±8	5,595	—
6	—	llama-3.1-70b-instructOpenMeta	1,209	±4	26,253	—
7	—	gemma-2-27b-itOpenGoogle	1,203	±3	37,529	—
8	—	jamba-1.5-largeOpenAI21 Labs	1,201	±6	9,191	—
9	—	gemma-2-9b-it-simpoOpenPrinceton	1,197	±5	10,617	—
10	—	nemotron-4-340b-instructOpenNVIDIA	1,196	±4	20,650	—
11	—	llama-3-70b-instructOpenMeta	1,194	±3	163,849	—
12	—	command-r-plus-08-2024OpenCohere	1,190	±7	5,653	—
13	—	command-r-plusOpenCohere	1,182	±3	80,852	—
14	—	qwen2-72b-instructOpenAlibaba	1,181	±3	38,976	—
15	—	deepseek-coder-v2OpenDeepSeek	1,179	±5	15,792	—
16	—	gemma-2-9b-itOpenGoogle	1,173	±4	30,237	—
17	—	command-r-08-2024OpenCohere	1,165	±8	5,837	—
18	▲ 1	qwen1.5-110b-chatOpenAlibaba	1,155	±4	27,451	—
19	▼ 1	jamba-1.5-miniOpenAI21 Labs	1,154	±6	9,305	—
20	—	mixtral-8x22b-instruct-v0.1OpenMistral	1,149	±3	53,817	—
21	—	qwen1.5-72b-chatOpenAlibaba	1,148	±3	40,604	—
22	—	command-rOpenCohere	1,148	±3	56,368	—
23	—	llama-3-8b-instructOpenMeta	1,141	±3	109,335	—
24	—	yi-1.5-34b-chatOpen01 AI	1,132	±4	25,134	—
25	—	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,131	±7	4,856	—
26	—	qwen1.5-32b-chatOpenAlibaba	1,127	±4	22,737	—
27	—	llama-3.1-8b-instructOpenMeta	1,120	±4	24,107	—
28	—	phi-3-medium-4k-instructOpenMicrosoft	1,117	±4	26,139	—
29	—	mixtral-8x7b-instruct-v0.1OpenMistral	1,114	±0	76,104	—
30	—	dbrx-instruct-previewOpenDatabricks	1,114	±3	33,713	—
31	▲ 1	wizardlm-70bOpenMicrosoft	1,108	±6	8,386	—
32	▼ 1	qwen1.5-14b-chatOpenAlibaba	1,107	±4	18,657	—
33	▲ 1	snowflake-arctic-instructOpenSnowflake	1,103	±4	34,167	—
34	▼ 1	gemma-2-2b-itOpenGoogle	1,102	±6	20,713	—
35	—	openchat-3.5-0106OpenOpenChat · 1 more variant	1,101	±4	12,978	—
36	—	yi-34b-chatOpen01 AI	1,101	±4	15,926	—
37	—	phi-3-small-8k-instructOpenMicrosoft	1,098	±5	18,489	—
38	—	gemma-1.1-7b-itOpenGoogle	1,097	±4	25,064	—
39	—	tulu-2-dpo-70bOpenAllenAI/UW	1,093	±7	6,660	—
40	—	vicuna-33bOpenLMSYS	1,092	±5	22,926	—
41	—	deepseek-llm-67b-chatOpenDeepSeek	1,091	±8	4,979	—
42	—	starling-lm-7b-betaOpenNexusflow	1,091	±4	16,661	—
43	—	openhermes-2.5-mistral-7bOpenNousResearch	1,091	±8	5,089	—
44	—	starling-lm-7b-alphaOpenUC Berkeley	1,084	±6	10,413	—
45	—	llama-2-70b-chatOpenMeta	1,082	±3	39,621	—
46	—	llama2-70b-steerlm-chatOpenNVIDIA	1,073	±10	3,635	—
47	—	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,072	±10	3,840	—
48	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,069	±6	12,889	—
49	▲ 3	wizardlm-13bOpenMicrosoft	1,067	±7	7,187	—
50	▼ 1	mistral-7b-instruct-v0.2OpenMistral	1,067	±5	20,046	—
51	▼ 1	qwen1.5-7b-chatOpenAlibaba	1,067	±7	4,859	—
52	▲ 1	falcon-180b-chatOpenTII	1,066	±19	1,326	—
53	▼ 2	solar-10.7b-instruct-v1.0OpenUpstage AI	1,066	±8	4,287	—
54	▲ 1	mpt-30b-chatOpenMosaicML	1,065	±12	2,650	—
55	▼ 1	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,065	±13	1,714	—
56	—	vicuna-13bOpenLMSYS	1,062	±6	19,789	—
57	—	qwen-14b-chatOpenAlibaba	1,058	±9	5,065	—
58	—	phi-3-mini-4k-instructOpenMicrosoft	1,054	±4	21,116	—
59	—	llama-2-13b-chatOpenMeta	1,053	±4	19,732	—
60	—	zephyr-7b-betaOpenHuggingFace	1,050	±5	11,322	—
61	—	phi-3-mini-128k-instructOpenMicrosoft	1,048	±5	21,609	—
62	—	codellama-34b-instructOpenMeta	1,047	±7	7,508	—
63	▲ 1	guanaco-33bOpenUW	1,047	±10	2,997	—
64	▼ 1	gemma-7b-itOpenGoogle	1,046	±6	9,177	—
65	—	zephyr-7b-alphaOpenHuggingFace	1,045	±13	1,816	—
66	▲ 2	codellama-70b-instructOpenMeta	1,037	±15	1,191	—
67	—	stripedhyena-nous-7bOpenTogether AI	1,036	±9	5,267	—
68	▼ 2	gemma-1.1-2b-itOpenGoogle	1,036	±6	11,355	—
69	▲ 1	llama-2-7b-chatOpenMeta	1,026	±5	14,553	—
70	▼ 1	mistral-7b-instructOpenMistral	1,026	±6	9,135	—
71	—	vicuna-7bOpenLMSYS	1,025	±7	7,018	—
72	—	qwen1.5-4b-chatOpenAlibaba	1,013	±6	7,802	—
73	—	gemma-2b-itOpenGoogle	1,013	±8	4,916	—
74	—	olmo-7b-instructOpenAi2	994	±10	6,491	—
75	—	gpt4all-13b-snoozyOpenNomic AI	994	±19	1,786	—
76	—	koala-13bOpenUC Berkeley	987	±8	7,033	—
77	▲ 1	alpaca-13bOpenStanford	977	±9	5,869	—
78	▼ 1	chatglm3-6bOpenTsinghua	976	±10	4,761	—
79	—	mpt-7b-chatOpenMosaicML	975	±12	4,015	—
80	—	RWKV-4-Raven-14BOpenRWKV	957	±11	4,934	—
81	—	oasst-pythia-12bOpenOpenAssistant	940	±10	6,380	—
82	—	chatglm2-6bOpenTsinghua	936	±14	2,707	—
83	—	fastchat-t5-3bOpenLMSYS	908	±13	4,301	—
84	—	chatglm-6bOpenTsinghua	899	±11	4,994	—
85	—	dolly-v2-12bOpenDatabricks	896	±13	3,486	—
86	—	llama-13bOpenMeta	886	±16	2,444	—
87	—	stablelm-tuned-alpha-7bOpenStability AI	872	±12	3,339	—

37 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