Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	glm-4.6OpenZ.ai	1,422	±9	4,401	—
2	—	deepseek-v3.2-exp-thinkingOpenDeepSeek · 1 more variant	1,419	±9	4,320	—
3	—	qwen3-vl-235b-a22b-instructOpenAlibaba	1,418	±8	6,312	—
4	—	qwen3-235b-a22b-instruct-2507OpenAlibaba	1,418	±5	29,343	—
5	—	deepseek-r1-0528OpenDeepSeek · 1 more variant	1,417	±6	19,284	—
6	—	kimi-k2-0905-previewOpenMoonshot AI · 1 more variant	1,417	±7	10,772	—
7	—	deepseek-v3.1OpenDeepSeek · 1 more variant	1,416	±6	15,380	—
8	—	deepseek-v3.1-terminusOpenDeepSeek · 1 more variant	1,414	±10	3,775	—
9	—	glm-4.5OpenZ.ai	1,406	±5	22,612	—
10	—	qwen3-next-80b-a3b-instructOpenAlibaba	1,402	±6	12,793	—
11	—	longcat-flash-chatOpenMeituan	1,398	±6	11,667	—
12	—	qwen3-235b-a22b-no-thinkingOpenAlibaba	1,398	±5	39,528	—
13	—	qwen3-235b-a22b-thinking-2507OpenAlibaba	1,397	±6	9,386	—
14	—	qwen3-vl-235b-a22b-thinkingOpenAlibaba	1,392	±8	5,956	—
15	—	deepseek-v3-0324OpenDeepSeek · 1 more variant	1,391	±4	44,482	—
16	—	qwen3-30b-a3b-instruct-2507OpenAlibaba	1,385	±5	21,853	—
17	—	qwen3-coder-480b-a35b-instructOpenAlibaba	1,384	±5	23,287	—
18	—	qwen3-235b-a22bOpenAlibaba	1,372	±5	27,210	—
19	—	glm-4.5-airOpenZ.ai	1,369	±5	21,945	—
20	—	minimax-m1OpenMiniMax	1,368	±5	31,897	—
21	—	qwen3-next-80b-a3b-thinkingOpenAlibaba	1,367	±6	11,522	—
22	—	gemma-3-27b-itOpenGoogle	1,363	±4	44,508	—
23	—	mistral-small-2506OpenMistral	1,353	±5	18,374	—
24	—	glm-4.5vOpenZ.ai	1,351	±8	5,028	—
25	—	command-a-03-2025OpenCohere	1,349	±4	47,441	—
26	—	gpt-oss-120bOpenOpenAI	1,348	±5	21,119	$0.26
27	—	llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA	1,344	±12	2,573	—
28	—	step-3OpenStepFun	1,344	±7	6,686	—
29	—	qwen3-32bOpenAlibaba	1,344	±9	3,943	—
30	—	ling-flash-2.0OpenAnt Group	1,341	±9	4,893	—
31	—	gemma-3-12b-itOpenGoogle	1,340	±9	3,866	—
32	—	nvidia-llama-3.3-nemotron-super-49b-v1.5OpenNVIDIA	1,339	±10	3,488	—
33	—	llama-3.1-405b-instruct-bf16OpenMeta	1,335	±4	41,932	—
34	—	llama-3.1-405b-instruct-fp8OpenMeta	1,333	±3	60,272	—
35	—	qwq-32bOpenAlibaba · 1 more variant	1,332	±4	26,309	—
36	—	llama-4-maverick-17b-128e-instructOpenMeta	1,327	±4	41,319	—
37	—	qwen3-30b-a3bOpenAlibaba	1,325	±5	27,520	—
38	—	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,324	±12	2,243	—
39	—	llama-4-scout-17b-16e-instructOpenMeta	1,322	±5	31,329	—
40	—	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,321	±8	6,877	—
41	—	llama-3.3-70b-instructOpenMeta	1,319	±3	56,024	—
42	—	gemma-3n-e4b-itOpenGoogle	1,318	±5	23,541	—
43	—	gpt-oss-20bOpenOpenAI	1,317	±6	10,906	—
44	—	qwen-max-0919OpenAlibaba	1,316	±6	16,598	—
45	—	ring-flash-2.0OpenAnt Group	1,314	±9	4,971	—
46	—	mistral-large-2407OpenMistral · 1 more variant	1,312	±4	45,968	—
47	—	athene-v2-chatOpenNexusFlow	1,312	±4	24,880	—
48	—	athene-70b-0725OpenNexusFlow	1,304	±6	19,796	—
49	—	gemma-3-4b-itOpenGoogle	1,302	±9	4,195	—
50	—	mistral-small-3.1-24b-instruct-2503OpenMistral	1,301	±5	31,747	—
51	—	qwen2.5-72b-instructOpenAlibaba	1,300	±4	39,632	—
52	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,296	±8	7,216	—
53	—	llama-3.1-70b-instructOpenMeta	1,292	±4	56,003	—
54	—	jamba-1.5-largeOpenAI21 Labs	1,287	±7	8,730	—
55	—	gemma-2-27b-itOpenGoogle	1,285	±3	76,195	—
56	—	llama-3.1-tulu-3-70bOpenAi2	1,285	±10	2,881	—
57	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,285	±10	3,777	—
58	—	ibm-granite-h-smallOpenIBM	1,285	±11	3,081	—
59	—	nemotron-4-340b-instructOpenNVIDIA	1,277	±5	19,913	—
60	—	gemma-2-9b-it-simpoOpenPrinceton	1,277	±7	10,108	—
61	—	command-r-plus-08-2024OpenCohere	1,276	±6	9,931	—
62	—	llama-3-70b-instructOpenMeta	1,275	±3	158,908	—
63	—	mistral-small-24b-instruct-2501OpenMistral	1,272	±6	14,830	—
64	—	qwen2.5-coder-32b-instructOpenAlibaba	1,268	±8	5,452	—
65	—	c4ai-aya-expanse-32bOpenCohere	1,266	±5	27,362	—
66	—	gemma-2-9b-itOpenGoogle	1,263	±4	54,954	—
67	—	command-r-plusOpenCohere	1,263	±4	78,401	—
68	—	deepseek-coder-v2OpenDeepSeek	1,262	±6	15,242	—
69	—	qwen2-72b-instructOpenAlibaba	1,261	±5	37,688	—
70	—	phi-4OpenMicrosoft	1,254	±4	24,354	—
71	—	olmo-2-0325-32b-instructOpenAi2	1,252	±11	3,377	—
72	—	command-r-08-2024OpenCohere	1,251	±6	10,229	—
73	—	jamba-1.5-miniOpenAI21 Labs	1,237	±7	8,918	—
74	—	ministral-8b-2410OpenMistral	1,235	±9	4,833	—
75	—	qwen1.5-110b-chatOpenAlibaba	1,234	±5	26,679	—
76	—	qwen1.5-72b-chatOpenAlibaba	1,233	±5	39,689	—
77	—	mixtral-8x22b-instruct-v0.1OpenMistral	1,229	±4	52,214	—
78	—	command-rOpenCohere	1,228	±5	54,710	—
79	—	c4ai-aya-expanse-8bOpenCohere	1,222	±7	9,922	—
80	—	llama-3-8b-instructOpenMeta	1,222	±4	106,055	—
81	—	llama-3.1-tulu-3-8bOpenAi2	1,221	±11	2,943	—
82	—	yi-1.5-34b-chatOpen01 AI	1,213	±5	24,417	—
83	—	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,213	±11	4,712	—
84	—	llama-3.1-8b-instructOpenMeta	1,210	±4	50,234	—
85	—	granite-3.1-8b-instructOpenIBM	1,209	±11	3,142	—
86	—	qwen1.5-32b-chatOpenAlibaba	1,205	±6	22,068	—
87	—	phi-3-medium-4k-instructOpenMicrosoft	1,198	±5	25,301	—
88	—	mixtral-8x7b-instruct-v0.1OpenMistral	1,197	±4	74,303	—
89	—	gemma-2-2b-itOpenGoogle	1,197	±4	46,901	—
90	—	dbrx-instruct-previewOpenDatabricks	1,195	±6	32,760	—
91	—	qwen1.5-14b-chatOpenAlibaba	1,192	±7	18,066	—
92	—	internlm2_5-20b-chatOpenInternLM	1,192	±7	10,038	—
93	—	wizardlm-70bOpenMicrosoft	1,185	±9	8,270	—
94	—	yi-34b-chatOpen01 AI	1,184	±7	15,624	—
95	—	deepseek-llm-67b-chatOpenDeepSeek	1,183	±11	4,950	—
96	—	granite-3.0-8b-instructOpenIBM	1,182	±9	6,727	—
97	—	openchat-3.5-0106OpenOpenChat · 1 more variant	1,182	±8	12,712	—
98	—	granite-3.1-2b-instructOpenIBM	1,180	±11	3,235	—
99	—	snowflake-arctic-instructOpenSnowflake	1,180	±6	33,272	—
100	—	tulu-2-dpo-70bOpenAllenAI/UW	1,179	±10	6,579	—
101	—	gemma-1.1-7b-itOpenGoogle	1,178	±6	24,327	—
102	—	openhermes-2.5-mistral-7bOpenNousResearch	1,175	±10	5,026	—
103	—	vicuna-33bOpenLMSYS	1,173	±6	22,613	—
104	—	starling-lm-7b-betaOpenNexusflow	1,173	±7	16,190	—
105	—	phi-3-small-8k-instructOpenMicrosoft	1,172	±6	17,983	—
106	—	llama-2-70b-chatOpenMeta	1,171	±5	38,767	—
107	—	starling-lm-7b-alphaOpenUC Berkeley	1,168	±8	10,267	—
108	—	llama-3.2-3b-instructOpenMeta	1,166	±8	8,043	—
109	—	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,166	±12	3,792	—
110	—	llama2-70b-steerlm-chatOpenNVIDIA	1,157	±13	3,605	—
111	—	granite-3.0-2b-instructOpenIBM	1,156	±8	6,922	—
112	—	solar-10.7b-instruct-v1.0OpenUpstage AI	1,154	±13	4,187	—
113	—	mistral-7b-instruct-v0.2OpenMistral	1,150	±7	19,603	—
114	—	mpt-30b-chatOpenMosaicML	1,150	±12	2,606	—
115	—	wizardlm-13bOpenMicrosoft	1,149	±9	7,122	—
116	—	qwen1.5-7b-chatOpenAlibaba	1,144	±10	4,782	—
117	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,143	±6	12,415	—
118	—	llama-2-13b-chatOpenMeta	1,142	±7	19,357	—
119	—	vicuna-13bOpenLMSYS	1,141	±7	19,539	—
120	—	qwen-14b-chatOpenAlibaba	1,138	±11	5,004	—
121	—	codellama-34b-instructOpenMeta	1,136	±9	7,417	—
122	—	gemma-7b-itOpenGoogle	1,133	±9	9,034	—
123	—	zephyr-7b-betaOpenHuggingFace	1,132	±9	11,220	—
124	—	phi-3-mini-128k-instructOpenMicrosoft	1,130	±7	21,024	—
125	—	phi-3-mini-4k-instructOpenMicrosoft	1,129	±6	20,539	—
126	—	guanaco-33bOpenUW	1,128	±12	2,955	—
127	—	stripedhyena-nous-7bOpenTogether AI	1,120	±11	5,214	—
128	—	smollm2-1.7b-instructOpenHuggingFace	1,118	±14	2,244	—
129	—	vicuna-7bOpenLMSYS	1,114	±9	6,972	—
130	—	llama-3.2-1b-instructOpenMeta	1,112	±8	8,166	—
131	—	gemma-1.1-2b-itOpenGoogle	1,112	±8	11,035	—
132	—	mistral-7b-instructOpenMistral	1,110	±9	9,042	—
133	—	llama-2-7b-chatOpenMeta	1,108	±7	14,272	—
134	—	qwen1.5-4b-chatOpenAlibaba	1,090	±9	7,662	—
135	—	gemma-2b-itOpenGoogle	1,089	±11	4,817	—
136	—	olmo-7b-instructOpenAi2	1,075	±11	6,412	—
137	—	koala-13bOpenUC Berkeley	1,070	±10	6,998	—
138	—	alpaca-13bOpenStanford	1,064	±11	5,828	—
139	—	mpt-7b-chatOpenMosaicML	1,060	±12	3,977	—
140	—	chatglm3-6bOpenTsinghua	1,056	±12	4,692	—
141	—	RWKV-4-Raven-14BOpenRWKV	1,041	±11	4,898	—
142	—	chatglm2-6bOpenTsinghua	1,025	±14	2,683	—
143	—	oasst-pythia-12bOpenOpenAssistant	1,021	±11	6,343	—
144	—	chatglm-6bOpenTsinghua	995	±13	4,968	—
145	—	fastchat-t5-3bOpenLMSYS	990	±12	4,270	—
146	—	dolly-v2-12bOpenDatabricks	977	±14	3,471	—
147	—	llama-13bOpenMeta	968	±16	2,441	—
148	—	stablelm-tuned-alpha-7bOpenStability AI	952	±13	3,325	—

98 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