Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	gemini-2.5-proClosedGoogle	1,456	±5	46,291	—
2	—	claude-opus-4-1-20250805-thinking-16kClosedAnthropic	1,449	±6	14,843	—
3	—	o3-2025-04-16ClosedOpenAI	1,441	±4	46,083	—
4	—	chatgpt-4o-latest-20250326ClosedOpenAI	1,441	±5	35,807	—
5	—	gpt-4.5-preview-2025-02-27ClosedOpenAI	1,441	±6	14,644	—
6	—	gpt-5-highClosedOpenAI	1,440	±6	17,636	—
7	—	claude-opus-4-1-20250805ClosedAnthropic	1,438	±6	23,612	—
8	—	gpt-5-chatClosedOpenAI	1,430	±6	14,876	—
9	—	claude-opus-4-20250514-thinking-16kClosedAnthropic	1,421	±5	30,101	—
10	—	grok-4-0709ClosedxAI	1,420	±5	23,994	—
11	—	gpt-4.1-2025-04-14ClosedOpenAI	1,411	±5	36,527	—
12	—	grok-3-preview-02-24ClosedxAI	1,410	±4	35,154	—
13	—	claude-opus-4-20250514ClosedAnthropic	1,410	±5	38,104	—
14	—	gemini-2.5-flashClosedGoogle	1,406	±5	47,004	—
15	—	claude-sonnet-4-20250514-thinking-32kClosedAnthropic	1,399	±5	28,637	—
16	—	o1-2024-12-17ClosedOpenAI	1,399	±4	28,039	—
17	—	o4-mini-2025-04-16ClosedOpenAI	1,392	±5	36,291	—
18	—	mai-1-previewClosedMicrosoft AI	1,391	±7	9,951	—
19	—	gpt-5-mini-highClosedOpenAI	1,389	±7	12,733	—
20	—	claude-sonnet-4-20250514ClosedAnthropic	1,386	±5	34,172	—
21	—	o1-previewClosedOpenAI	1,385	±5	31,505	—
22	—	claude-3-7-sonnet-20250219-thinking-32kClosedAnthropic	1,385	±4	36,956	—
23	—	gemini-2.5-flash-lite-preview-06-17-thinkingClosedGoogle	1,378	±5	26,274	—
24	—	gpt-4.1-mini-2025-04-14ClosedOpenAI	1,375	±5	36,061	—
25	—	claude-3-7-sonnet-20250219ClosedAnthropic	1,369	±4	41,863	—
26	—	claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant	1,368	±3	86,848	—
27	—	gemma-3-27b-itOpenGoogle	1,363	±4	39,569	—
28	—	grok-3-mini-highClosedxAI	1,362	±6	14,820	—
29	—	gemini-2.0-flash-001ClosedGoogle	1,362	±4	42,303	—
30	—	o3-mini-highClosedOpenAI	1,361	±5	18,735	—
31	—	grok-3-mini-betaClosedxAI	1,357	±5	21,142	—
32	—	gemini-2.0-flash-lite-preview-02-05ClosedGoogle	1,351	±4	25,215	—
33	—	gpt-oss-120bOpenOpenAI	1,350	±6	14,753	$0.26
34	—	gemini-1.5-pro-002ClosedGoogle	1,350	±3	56,012	—
35	—	o3-miniClosedOpenAI	1,346	±4	54,461	—
36	—	llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA	1,344	±12	2,573	—
37	—	gpt-5-nano-highClosedOpenAI	1,344	±9	4,775	—
38	—	gpt-4o-2024-05-13ClosedOpenAI	1,342	±3	113,568	—
39	—	nvidia-llama-3.3-nemotron-super-49b-v1.5OpenNVIDIA	1,340	±10	3,625	—
40	—	gemma-3-12b-itOpenGoogle	1,339	±10	3,866	—
41	—	o1-miniClosedOpenAI	1,333	±4	52,301	—
42	—	llama-3.1-405b-instruct-bf16OpenMeta	1,333	±4	41,932	—
43	—	gpt-4o-2024-08-06ClosedOpenAI	1,332	±4	45,787	—
44	—	grok-2-2024-08-13ClosedxAI	1,332	±4	63,725	—
45	—	llama-3.1-405b-instruct-fp8OpenMeta	1,331	±3	60,272	—
46	—	gemini-advanced-0514ClosedGoogle	1,331	±5	50,654	—
47	—	gpt-oss-20bOpenOpenAI	1,325	±7	7,197	—
48	—	llama-4-maverick-17b-128e-instructOpenMeta	1,325	±4	36,588	—
49	—	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,324	±12	2,243	—
50	—	gpt-4-turbo-2024-04-09ClosedOpenAI	1,321	±4	98,965	—
51	—	claude-3-opus-20240229ClosedAnthropic	1,319	±3	196,368	—
52	—	gemini-1.5-pro-001ClosedGoogle	1,319	±4	79,769	—
53	—	llama-4-scout-17b-16e-instructOpenMeta	1,319	±5	26,364	—
54	—	gpt-4.1-nano-2025-04-14ClosedOpenAI	1,318	±8	6,143	—
55	—	gemma-3n-e4b-itOpenGoogle	1,318	±5	24,134	—
56	—	claude-3-5-haiku-20241022ClosedAnthropic	1,317	±3	66,793	—
57	—	llama-3.3-70b-instructOpenMeta	1,316	±3	52,593	—
58	—	gpt-4o-mini-2024-07-18ClosedOpenAI	1,314	±3	69,331	—
59	—	gpt-4-1106-previewClosedOpenAI	1,311	±4	101,117	—
60	—	gpt-4-0125-previewClosedOpenAI	1,311	±4	94,534	—
61	—	gemini-1.5-flash-002ClosedGoogle	1,309	±4	35,180	—
62	—	grok-2-mini-2024-08-13ClosedxAI	1,305	±4	52,789	—
63	—	gemma-3-4b-itOpenGoogle	1,301	±9	4,195	—
64	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,296	±8	7,216	—
65	—	llama-3.1-70b-instructOpenMeta	1,291	±4	56,003	—
66	—	amazon-nova-pro-v1.0ClosedAmazon	1,286	±4	25,218	—
67	—	llama-3.1-tulu-3-70bOpenAi2	1,284	±10	2,881	—
68	—	gemma-2-27b-itOpenGoogle	1,284	±3	76,195	—
69	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,284	±10	3,777	—
70	—	gpt-4-0314ClosedOpenAI	1,283	±5	54,754	—
71	—	gemini-1.5-flash-001ClosedGoogle	1,282	±4	63,418	—
72	—	claude-3-sonnet-20240229ClosedAnthropic	1,278	±4	110,173	—
73	—	nemotron-4-340b-instructOpenNVIDIA	1,276	±5	19,913	—
74	—	llama-3-70b-instructOpenMeta	1,273	±3	158,908	—
75	—	gpt-4-0613ClosedOpenAI	1,272	±4	89,612	—
76	—	gemma-2-9b-itOpenGoogle	1,261	±4	54,954	—
77	—	claude-3-haiku-20240307ClosedAnthropic	1,258	±4	118,626	—
78	—	amazon-nova-lite-v1.0ClosedAmazon	1,258	±5	19,760	—
79	—	gemini-1.5-flash-8b-001ClosedGoogle	1,258	±4	35,914	—
80	—	phi-4OpenMicrosoft	1,253	±5	24,354	—
81	—	olmo-2-0325-32b-instructOpenAi2	1,251	±11	3,377	—
82	—	amazon-nova-micro-v1.0ClosedAmazon	1,240	±5	19,774	—
83	—	gemini-pro-dev-apiClosedGoogle	1,230	±7	18,454	—
84	—	llama-3-8b-instructOpenMeta	1,221	±4	106,055	—
85	—	llama-3.1-tulu-3-8bOpenAi2	1,221	±11	2,943	—
86	—	gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant	1,220	±5	67,214	—
87	—	gemini-proClosedGoogle	1,217	±12	6,418	—
88	—	llama-3.1-8b-instructOpenMeta	1,210	±4	50,234	—
89	—	granite-3.1-8b-instructOpenIBM	1,208	±11	3,142	—
90	—	phi-3-medium-4k-instructOpenMicrosoft	1,196	±5	25,301	—
91	—	gemma-2-2b-itOpenGoogle	1,195	±4	46,901	—
92	—	dbrx-instruct-previewOpenDatabricks	1,193	±6	32,760	—
93	—	wizardlm-70bOpenMicrosoft	1,183	±9	8,270	—
94	—	granite-3.0-8b-instructOpenIBM	1,180	±9	6,727	—
95	—	granite-3.1-2b-instructOpenIBM	1,179	±11	3,235	—
96	—	snowflake-arctic-instructOpenSnowflake	1,177	±6	33,272	—
97	—	gemma-1.1-7b-itOpenGoogle	1,175	±6	24,327	—
98	—	phi-3-small-8k-instructOpenMicrosoft	1,170	±6	17,983	—
99	—	llama-2-70b-chatOpenMeta	1,169	±5	38,767	—
100	—	llama-3.2-3b-instructOpenMeta	1,165	±8	8,043	—
101	—	llama2-70b-steerlm-chatOpenNVIDIA	1,155	±13	3,605	—
102	—	granite-3.0-2b-instructOpenIBM	1,154	±8	6,922	—
103	—	wizardlm-13bOpenMicrosoft	1,148	±9	7,122	—
104	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,141	±6	12,415	—
105	—	llama-2-13b-chatOpenMeta	1,140	±7	19,357	—
106	—	codellama-34b-instructOpenMeta	1,134	±9	7,417	—
107	—	palm-2ClosedGoogle	1,133	±9	8,634	—
108	—	gemma-7b-itOpenGoogle	1,131	±9	9,034	—
109	—	phi-3-mini-128k-instructOpenMicrosoft	1,128	±7	21,024	—
110	—	phi-3-mini-4k-instructOpenMicrosoft	1,127	±6	20,539	—
111	—	llama-3.2-1b-instructOpenMeta	1,111	±8	8,166	—
112	—	gemma-1.1-2b-itOpenGoogle	1,109	±8	11,035	—
113	—	llama-2-7b-chatOpenMeta	1,107	±7	14,272	—
114	—	gemma-2b-itOpenGoogle	1,087	±12	4,817	—
115	—	olmo-7b-instructOpenAi2	1,073	±11	6,412	—
116	—	dolly-v2-12bOpenDatabricks	975	±14	3,471	—
117	—	llama-13bOpenMeta	966	±16	2,441	—

67 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