Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	gemini-2.5-proClosedGoogle	1,451	±4	54,087	—
2	—	claude-opus-4-1-20250805-thinking-16kClosedAnthropic	1,447	±5	21,306	—
3	—	claude-sonnet-4-5-20250929-thinking-32kClosedAnthropic	1,445	±8	6,287	—
4	—	gpt-4.5-preview-2025-02-27ClosedOpenAI	1,441	±6	14,644	—
5	—	chatgpt-4o-latest-20250326ClosedOpenAI	1,440	±4	40,013	—
6	—	o3-2025-04-16ClosedOpenAI	1,440	±4	51,293	—
7	—	claude-sonnet-4-5-20250929ClosedAnthropic	1,438	±8	6,144	—
8	—	gpt-5-highClosedOpenAI	1,437	±5	23,580	—
9	—	claude-opus-4-1-20250805ClosedAnthropic	1,437	±5	33,298	—
10	—	gpt-5-chatClosedOpenAI	1,425	±5	21,630	—
11	—	grok-4-fast-chatClosedxAI	1,420	±8	7,104	—
12	—	claude-opus-4-20250514-thinking-16kClosedAnthropic	1,419	±5	35,522	—
13	—	grok-4-0709ClosedxAI	1,413	±5	29,264	—
14	—	claude-opus-4-20250514ClosedAnthropic	1,411	±4	43,310	—
15	—	gpt-4.1-2025-04-14ClosedOpenAI	1,411	±4	41,918	—
16	—	grok-3-preview-02-24ClosedxAI	1,409	±4	34,154	—
17	—	gemini-2.5-flashClosedGoogle	1,407	±4	53,364	—
18	—	gemini-2.5-flash-preview-09-2025ClosedGoogle	1,404	±7	6,730	—
19	—	grok-4-fast-reasoningClosedxAI	1,402	±8	5,571	—
20	—	o1-2024-12-17ClosedOpenAI	1,400	±4	28,039	—
21	—	claude-sonnet-4-20250514-thinking-32kClosedAnthropic	1,398	±5	33,827	—
22	—	claude-haiku-4-5-20251001ClosedAnthropic	1,397	±12	2,380	$2.0
23	—	gpt-5-mini-highClosedOpenAI	1,395	±6	18,172	—
24	—	o4-mini-2025-04-16ClosedOpenAI	1,391	±4	41,513	—
25	—	claude-sonnet-4-20250514ClosedAnthropic	1,389	±5	39,329	—
26	—	mai-1-previewClosedMicrosoft AI	1,389	±6	14,528	—
27	—	o1-previewClosedOpenAI	1,386	±5	31,505	—
28	—	claude-3-7-sonnet-20250219-thinking-32kClosedAnthropic	1,386	±4	39,987	—
29	—	gpt-4.1-mini-2025-04-14ClosedOpenAI	1,379	±4	40,621	—
30	—	gemini-2.5-flash-lite-preview-06-17-thinkingClosedGoogle	1,374	±5	31,701	—
31	—	gemini-2.5-flash-lite-preview-09-2025-no-thinkingClosedGoogle	1,374	±7	6,765	—
32	—	claude-3-5-sonnet-20241022ClosedAnthropic · 1 more variant	1,370	±3	89,889	—
33	—	claude-3-7-sonnet-20250219ClosedAnthropic	1,370	±4	44,619	—
34	—	gemma-3-27b-itOpenGoogle	1,363	±4	44,508	—
35	—	grok-3-mini-highClosedxAI	1,362	±5	17,615	—
36	—	o3-mini-highClosedOpenAI	1,362	±5	18,735	—
37	—	gemini-2.0-flash-001ClosedGoogle	1,360	±4	45,135	—
38	—	grok-3-mini-betaClosedxAI	1,356	±5	23,839	—
39	—	gemini-2.0-flash-lite-preview-02-05ClosedGoogle	1,352	±4	25,215	—
40	—	gemini-1.5-pro-002ClosedGoogle	1,351	±3	56,012	—
41	—	gpt-oss-120bOpenOpenAI	1,348	±5	21,119	$0.26
42	—	o3-miniClosedOpenAI	1,347	±3	58,935	—
43	—	llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA	1,344	±12	2,573	—
44	—	amazon-nova-experimental-chat-10-09ClosedAmazon	1,344	±11	2,911	—
45	—	gpt-4o-2024-05-13ClosedOpenAI	1,344	±3	113,568	—
46	—	gemma-3-12b-itOpenGoogle	1,340	±9	3,866	—
47	—	nvidia-llama-3.3-nemotron-super-49b-v1.5OpenNVIDIA	1,339	±10	3,488	—
48	—	gpt-5-nano-highClosedOpenAI	1,337	±7	8,465	—
49	—	llama-3.1-405b-instruct-bf16OpenMeta	1,335	±4	41,932	—
50	—	o1-miniClosedOpenAI	1,334	±3	52,301	—
51	—	gpt-4o-2024-08-06ClosedOpenAI	1,333	±4	45,787	—
52	—	llama-3.1-405b-instruct-fp8OpenMeta	1,333	±3	60,272	—
53	—	grok-2-2024-08-13ClosedxAI	1,333	±3	63,725	—
54	—	gemini-advanced-0514ClosedGoogle	1,332	±5	50,654	—
55	—	llama-4-maverick-17b-128e-instructOpenMeta	1,327	±4	41,319	—
56	—	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,324	±12	2,243	—
57	—	gpt-4-turbo-2024-04-09ClosedOpenAI	1,323	±4	98,965	—
58	—	llama-4-scout-17b-16e-instructOpenMeta	1,322	±5	31,329	—
59	—	claude-3-opus-20240229ClosedAnthropic	1,321	±3	196,368	—
60	—	claude-3-5-haiku-20241022ClosedAnthropic	1,320	±3	71,507	—
61	—	gemini-1.5-pro-001ClosedGoogle	1,320	±4	79,769	—
62	—	gpt-4.1-nano-2025-04-14ClosedOpenAI	1,319	±8	6,143	—
63	—	llama-3.3-70b-instructOpenMeta	1,319	±3	56,024	—
64	—	gemma-3n-e4b-itOpenGoogle	1,318	±5	23,541	—
65	—	gpt-oss-20bOpenOpenAI	1,317	±6	10,906	—
66	—	gpt-4o-mini-2024-07-18ClosedOpenAI	1,315	±3	69,290	—
67	—	gpt-4-1106-previewClosedOpenAI	1,313	±4	101,117	—
68	—	gpt-4-0125-previewClosedOpenAI	1,313	±4	94,534	—
69	—	gemini-1.5-flash-002ClosedGoogle	1,310	±4	35,180	—
70	—	grok-2-mini-2024-08-13ClosedxAI	1,306	±4	52,789	—
71	—	gemma-3-4b-itOpenGoogle	1,302	±9	4,195	—
72	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,296	±8	7,216	—
73	—	llama-3.1-70b-instructOpenMeta	1,292	±4	56,003	—
74	—	amazon-nova-pro-v1.0ClosedAmazon	1,287	±4	25,218	—
75	—	gemma-2-27b-itOpenGoogle	1,285	±3	76,195	—
76	—	llama-3.1-tulu-3-70bOpenAi2	1,285	±10	2,881	—
77	—	gpt-4-0314ClosedOpenAI	1,285	±5	54,754	—
78	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,285	±10	3,777	—
79	—	ibm-granite-h-smallOpenIBM	1,285	±11	3,081	—
80	—	gemini-1.5-flash-001ClosedGoogle	1,283	±4	63,418	—
81	—	claude-3-sonnet-20240229ClosedAnthropic	1,280	±4	110,173	—
82	—	nemotron-4-340b-instructOpenNVIDIA	1,277	±5	19,913	—
83	—	llama-3-70b-instructOpenMeta	1,275	±3	158,908	—
84	—	gpt-4-0613ClosedOpenAI	1,274	±4	89,612	—
85	—	gemma-2-9b-itOpenGoogle	1,263	±4	54,954	—
86	—	claude-3-haiku-20240307ClosedAnthropic	1,260	±4	118,626	—
87	—	gemini-1.5-flash-8b-001ClosedGoogle	1,259	±4	35,914	—
88	—	amazon-nova-lite-v1.0ClosedAmazon	1,259	±5	19,760	—
89	—	phi-4OpenMicrosoft	1,254	±4	24,354	—
90	—	olmo-2-0325-32b-instructOpenAi2	1,252	±11	3,377	—
91	—	amazon-nova-micro-v1.0ClosedAmazon	1,240	±5	19,774	—
92	—	gemini-pro-dev-apiClosedGoogle	1,233	±7	18,454	—
93	—	gpt-3.5-turbo-0125ClosedOpenAI · 1 more variant	1,223	±5	67,214	—
94	—	llama-3-8b-instructOpenMeta	1,222	±4	106,055	—
95	—	llama-3.1-tulu-3-8bOpenAi2	1,221	±11	2,943	—
96	—	gemini-proClosedGoogle	1,220	±12	6,418	—
97	—	llama-3.1-8b-instructOpenMeta	1,210	±4	50,234	—
98	—	granite-3.1-8b-instructOpenIBM	1,209	±11	3,142	—
99	—	phi-3-medium-4k-instructOpenMicrosoft	1,198	±5	25,301	—
100	—	gemma-2-2b-itOpenGoogle	1,197	±4	46,901	—
101	—	dbrx-instruct-previewOpenDatabricks	1,195	±6	32,760	—
102	—	wizardlm-70bOpenMicrosoft	1,185	±9	8,270	—
103	—	granite-3.0-8b-instructOpenIBM	1,182	±9	6,727	—
104	—	granite-3.1-2b-instructOpenIBM	1,180	±11	3,235	—
105	—	snowflake-arctic-instructOpenSnowflake	1,180	±6	33,272	—
106	—	gemma-1.1-7b-itOpenGoogle	1,178	±6	24,327	—
107	—	phi-3-small-8k-instructOpenMicrosoft	1,172	±6	17,983	—
108	—	llama-2-70b-chatOpenMeta	1,171	±5	38,767	—
109	—	llama-3.2-3b-instructOpenMeta	1,166	±8	8,043	—
110	—	llama2-70b-steerlm-chatOpenNVIDIA	1,157	±13	3,605	—
111	—	granite-3.0-2b-instructOpenIBM	1,156	±8	6,922	—
112	—	wizardlm-13bOpenMicrosoft	1,149	±9	7,122	—
113	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,143	±6	12,415	—
114	—	llama-2-13b-chatOpenMeta	1,142	±7	19,357	—
115	—	codellama-34b-instructOpenMeta	1,136	±9	7,417	—
116	—	palm-2ClosedGoogle	1,135	±9	8,634	—
117	—	gemma-7b-itOpenGoogle	1,133	±9	9,034	—
118	—	phi-3-mini-128k-instructOpenMicrosoft	1,130	±7	21,024	—
119	—	phi-3-mini-4k-instructOpenMicrosoft	1,129	±6	20,539	—
120	—	llama-3.2-1b-instructOpenMeta	1,112	±8	8,166	—
121	—	gemma-1.1-2b-itOpenGoogle	1,112	±8	11,035	—
122	—	llama-2-7b-chatOpenMeta	1,108	±7	14,272	—
123	—	gemma-2b-itOpenGoogle	1,089	±11	4,817	—
124	—	olmo-7b-instructOpenAi2	1,075	±11	6,412	—
125	—	dolly-v2-12bOpenDatabricks	977	±14	3,471	—
126	—	llama-13bOpenMeta	968	±16	2,441	—

76 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