Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	chatgpt-4o-latestClosedOpenAI	1,289	±5	24,023	—
2	—	gpt-4o-2024-05-13ClosedOpenAI	1,261	±3	82,934	—
3	—	claude-3-5-sonnet-20240620ClosedAnthropic	1,258	±4	53,352	—
4	—	gemini-advanced-0514ClosedGoogle	1,251	±4	52,225	—
5	—	grok-2-2024-08-13ClosedxAI	1,250	±6	10,019	—
6	—	llama-3.1-405b-instructOpenMeta	1,250	±5	24,584	—
7	—	gpt-4o-2024-08-06ClosedOpenAI	1,245	±5	14,886	—
8	—	gpt-4-turbo-2024-04-09ClosedOpenAI	1,240	±3	88,005	—
9	—	claude-3-opus-20240229ClosedAnthropic	1,237	±3	159,592	—
10	—	gemini-1.5-pro-api-0514ClosedGoogle	1,236	±3	74,660	—
11	—	gpt-4-1106-previewClosedOpenAI	1,234	±3	94,283	—
12	—	gpt-4o-mini-2024-07-18ClosedOpenAI	1,231	±4	23,147	—
13	—	gpt-4-0125-previewClosedOpenAI	1,230	±3	87,597	—
14	—	mistral-large-2407OpenMistral · 1 more variant	1,228	±5	17,036	—
15	—	athene-70b-0725OpenNexusFlow	1,217	±5	15,167	—
16	—	grok-2-mini-2024-08-13ClosedxAI	1,216	±6	10,791	—
17	—	llama-3.1-70b-instructOpenMeta	1,210	±4	19,220	—
18	—	gemma-2-27b-itOpenGoogle	1,202	±4	31,513	—
19	—	gpt-4-0314ClosedOpenAI	1,201	±3	55,950	—
20	—	gemini-1.5-flash-api-0514ClosedGoogle	1,200	±3	59,852	—
21	—	claude-3-sonnet-20240229ClosedAnthropic	1,197	±2	113,031	—
22	—	nemotron-4-340b-instructOpenNVIDIA	1,195	±4	20,658	—
23	—	jamba-1.5-largeOpenAI21 Labs	1,193	±9	5,281	—
24	—	llama-3-70b-instructOpenMeta	1,193	±2	163,635	—
25	—	glm-4-0520ClosedZhipu AI	1,187	±6	10,230	—
26	—	gpt-4-0613ClosedOpenAI	1,187	±2	91,361	—
27	—	command-r-plusOpenCohere	1,182	±2	80,901	—
28	—	deepseek-coder-v2OpenDeepSeek	1,180	±5	15,790	—
29	—	qwen2-72b-instructOpenAlibaba	1,180	±3	36,278	—
30	—	claude-3-haiku-20240307ClosedAnthropic	1,176	±2	111,796	—
31	—	gemma-2-9b-itOpenGoogle	1,173	±4	27,150	—
32	—	jamba-1.5-miniOpenAI21 Labs	1,155	±9	5,266	—
33	—	qwen1.5-110b-chatOpenAlibaba	1,154	±4	27,474	—
34	—	reka-flash-21b-20240226-onlineClosedReka AI	1,151	±5	16,033	—
35	—	mixtral-8x22b-instruct-v0.1OpenMistral	1,148	±3	52,139	—
36	—	qwen1.5-72b-chatOpenAlibaba	1,148	±4	40,616	—
37	—	command-rOpenCohere	1,148	±3	56,371	—
38	—	gemini-pro-dev-apiClosedGoogle	1,147	±5	18,784	—
39	—	mistral-mediumClosedMistral	1,141	±3	35,547	—
40	—	reka-flash-21b-20240226ClosedReka AI	1,141	±4	25,785	—
41	—	llama-3-8b-instructOpenMeta	1,141	±3	109,023	—
42	—	gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant	1,138	±2	68,884	—
43	—	gemini-proClosedGoogle	1,132	±8	6,560	—
44	—	yi-1.5-34b-chatOpen01 AI	1,131	±4	25,163	—
45	—	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,131	±7	4,855	—
46	—	qwen1.5-32b-chatOpenAlibaba	1,127	±5	22,755	—
47	—	phi-3-medium-4k-instructOpenMicrosoft	1,118	±4	24,305	—
48	—	llama-3.1-8b-instructOpenMeta	1,117	±4	18,335	—
49	—	mixtral-8x7b-instruct-v0.1OpenMistral	1,114	±0	76,119	—
50	—	dbrx-instruct-previewOpenDatabricks	1,113	±4	33,728	—
51	—	qwen1.5-14b-chatOpenAlibaba	1,106	±4	18,666	—
52	—	wizardlm-70bOpenMicrosoft	1,106	±7	8,386	—
53	—	gemma-2-2b-itOpenGoogle	1,103	±6	14,379	—
54	—	snowflake-arctic-instructOpenSnowflake	1,102	±4	34,184	—
55	—	openchat-3.5-0106OpenOpenChat · 1 more variant	1,101	±5	12,975	—
56	—	yi-34b-chatOpen01 AI	1,100	±5	15,923	—
57	—	phi-3-small-8k-instructOpenMicrosoft	1,097	±5	18,493	—
58	—	gemma-1.1-7b-itOpenGoogle	1,097	±4	25,073	—
59	—	tulu-2-dpo-70bOpenAllenAI/UW	1,093	±7	6,655	—
60	—	vicuna-33bOpenLMSYS	1,092	±4	22,937	—
61	—	deepseek-llm-67b-chatOpenDeepSeek	1,091	±8	4,982	—
62	—	openhermes-2.5-mistral-7bOpenNousResearch	1,090	±8	5,090	—
63	—	starling-lm-7b-betaOpenNexusflow	1,090	±5	16,659	—
64	—	starling-lm-7b-alphaOpenUC Berkeley	1,083	±5	10,413	—
65	—	llama-2-70b-chatOpenMeta	1,081	±4	39,621	—
66	—	llama2-70b-steerlm-chatOpenNVIDIA	1,073	±8	3,634	—
67	—	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,071	±10	3,841	—
68	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,067	±7	12,519	—
69	—	mistral-7b-instruct-v0.2OpenMistral	1,067	±4	20,058	—
70	—	qwen1.5-7b-chatOpenAlibaba	1,066	±9	4,857	—
71	—	solar-10.7b-instruct-v1.0OpenUpstage AI	1,066	±8	4,291	—
72	—	wizardlm-13bOpenMicrosoft	1,065	±6	7,187	—
73	—	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,063	±13	1,713	—
74	—	mpt-30b-chatOpenMosaicML	1,062	±11	2,649	—
75	—	falcon-180b-chatOpenTII	1,062	±15	1,325	—
76	—	vicuna-13bOpenLMSYS	1,060	±5	19,788	—
77	—	qwen-14b-chatOpenAlibaba	1,057	±8	5,067	—
78	—	phi-3-mini-4k-instructOpenMicrosoft	1,055	±4	21,111	—
79	—	llama-2-13b-chatOpenMeta	1,053	±5	19,720	—
80	—	zephyr-7b-betaOpenHuggingFace	1,049	±6	11,318	—
81	—	phi-3-mini-128k-instructOpenMicrosoft	1,049	±4	21,588	—
82	—	codellama-34b-instructOpenMeta	1,046	±6	7,510	—
83	—	palm-2ClosedGoogle	1,046	±7	8,744	—
84	—	gemma-7b-itOpenGoogle	1,045	±6	9,174	—
85	—	guanaco-33bOpenUW	1,043	±11	3,000	—
86	—	zephyr-7b-alphaOpenHuggingFace	1,042	±13	1,816	—
87	—	gemma-1.1-2b-itOpenGoogle	1,036	±6	11,356	—
88	—	stripedhyena-nous-7bOpenTogether AI	1,035	±8	5,266	—
89	—	codellama-70b-instructOpenMeta	1,033	±19	1,193	—
90	—	mistral-7b-instructOpenMistral	1,026	±7	9,138	—
91	—	llama-2-7b-chatOpenMeta	1,024	±5	14,556	—
92	—	vicuna-7bOpenLMSYS	1,023	±8	7,018	—
93	—	qwen1.5-4b-chatOpenAlibaba	1,014	±7	7,801	—
94	—	gemma-2b-itOpenGoogle	1,011	±7	4,920	—
95	—	olmo-7b-instructOpenAi2	993	±8	6,494	—
96	—	gpt4all-13b-snoozyOpenNomic AI	987	±18	1,786	—
97	—	koala-13bOpenUC Berkeley	983	±8	7,039	—
98	—	chatglm3-6bOpenTsinghua	975	±9	4,761	—
99	—	alpaca-13bOpenStanford	974	±8	5,873	—
100	—	mpt-7b-chatOpenMosaicML	971	±10	4,015	—
101	—	RWKV-4-Raven-14BOpenRWKV	953	±11	4,936	—
102	—	oasst-pythia-12bOpenOpenAssistant	936	±8	6,382	—
103	—	chatglm2-6bOpenTsinghua	934	±14	2,707	—
104	—	fastchat-t5-3bOpenLMSYS	903	±11	4,304	—
105	—	chatglm-6bOpenTsinghua	893	±10	4,992	—
106	—	dolly-v2-12bOpenDatabricks	890	±12	3,486	—
107	—	llama-13bOpenMeta	880	±18	2,443	—
108	—	stablelm-tuned-alpha-7bOpenStability AI	865	±13	3,337	—

58 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