Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	kimi-k2-thinking-turboOpenMoonshot AI	1,426	±6	15,621	—
2	—	glm-4.6OpenZ.ai	1,425	±5	24,502	—
3	—	deepseek-v3.2-expOpenDeepSeek · 1 more variant	1,423	±7	11,973	—
4	▲ 1	qwen3-235b-a22b-instruct-2507OpenAlibaba	1,421	±4	51,250	—
5	▲ 1	deepseek-v3.2-thinkingOpenDeepSeek · 1 more variant	1,418	±9	5,948	—
6	▲ 1	kimi-k2-0905-previewOpenMoonshot AI · 1 more variant	1,418	±7	11,836	—
7	▲ 1	deepseek-r1-0528OpenDeepSeek · 1 more variant	1,418	±6	19,236	—
8	▲ 1	deepseek-v3.1OpenDeepSeek · 1 more variant	1,416	±6	15,256	—
9	▼ 5	mistral-large-3OpenMistral	1,415	±8	6,377	—
10	▲ 1	qwen3-vl-235b-a22b-instructOpenAlibaba	1,415	±7	8,532	—
11	▼ 1	deepseek-v3.1-terminusOpenDeepSeek · 1 more variant	1,415	±10	3,745	—
12	—	glm-4.5OpenZ.ai	1,408	±5	24,820	—
13	—	qwen3-next-80b-a3b-instructOpenAlibaba	1,400	±5	23,111	—
14	—	longcat-flash-chatOpenMeituan	1,400	±6	11,498	—
15	—	qwen3-235b-a22b-no-thinkingOpenAlibaba	1,399	±4	39,375	—
16	—	qwen3-235b-a22b-thinking-2507OpenAlibaba	1,397	±6	9,345	—
17	—	qwen3-vl-235b-a22b-thinkingOpenAlibaba	1,394	±7	7,986	—
18	—	deepseek-v3-0324OpenDeepSeek · 1 more variant	1,392	±4	46,777	—
19	—	qwen3-coder-480b-a35b-instructOpenAlibaba	1,385	±5	23,148	—
20	—	qwen3-30b-a3b-instruct-2507OpenAlibaba	1,382	±5	24,190	—
21	—	qwen3-235b-a22bOpenAlibaba	1,374	±5	27,167	—
22	—	glm-4.5-airOpenZ.ai	1,370	±4	31,668	—
23	—	qwen3-next-80b-a3b-thinkingOpenAlibaba	1,367	±6	13,822	—
24	—	minimax-m1OpenMiniMax	1,366	±4	36,877	—
25	—	gemma-3-27b-itOpenGoogle	1,364	±4	49,312	—
26	—	mistral-small-2506OpenMistral	1,354	±5	18,325	—
27	—	gpt-oss-120bOpenOpenAI	1,352	±4	31,256	$0.26
28	—	command-a-03-2025OpenCohere	1,352	±3	57,820	—
29	—	glm-4.5vOpenZ.ai	1,352	±8	4,973	—
30	New	intellect-3OpenPrime Intellect	1,348	±13	2,020	—
31	▼ 1	ling-flash-2.0OpenAnt Group	1,346	±7	7,157	—
32	—	step-3OpenStepFun	1,346	±7	6,638	—
33	▼ 2	minimax-m2OpenMiniMax	1,345	±8	7,123	—
34	▼ 1	llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA	1,345	±12	2,573	—
35	▼ 1	qwen3-32bOpenAlibaba	1,344	±9	3,943	—
36	▼ 1	gemma-3-12b-itOpenGoogle	1,340	±9	3,866	—
37	▼ 1	nvidia-llama-3.3-nemotron-super-49b-v1.5OpenNVIDIA	1,340	±10	3,492	—
38	▼ 1	llama-3.1-405b-instruct-bf16OpenMeta	1,336	±4	41,932	—
39	—	llama-3.1-405b-instruct-fp8OpenMeta	1,334	±3	60,272	—
40	▼ 2	qwq-32bOpenAlibaba · 1 more variant	1,334	±4	26,269	—
41	▼ 1	llama-4-maverick-17b-128e-instructOpenMeta	1,327	±4	41,199	—
42	▼ 1	qwen3-30b-a3bOpenAlibaba	1,326	±5	27,485	—
43	▼ 1	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,326	±12	2,243	—
44	—	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,323	±8	6,877	—
45	▼ 2	llama-4-scout-17b-16e-instructOpenMeta	1,322	±5	31,193	—
46	▼ 1	ring-flash-2.0OpenAnt Group	1,320	±7	7,278	—
47	▼ 1	llama-3.3-70b-instructOpenMeta	1,319	±3	56,008	—
48	▼ 1	gemma-3n-e4b-itOpenGoogle	1,318	±5	23,470	—
49	—	qwen-max-0919OpenAlibaba	1,318	±6	16,598	—
50	▼ 2	gpt-oss-20bOpenOpenAI	1,318	±6	10,848	—
51	▼ 1	mistral-large-2407OpenMistral · 1 more variant	1,314	±4	45,968	—
52	▼ 1	athene-v2-chatOpenNexusFlow	1,313	±4	24,880	—
53	▼ 1	olmo-3-32b-thinkOpenAi2	1,306	±11	3,405	—
54	▼ 1	athene-70b-0725OpenNexusFlow	1,305	±6	19,796	—
55	▼ 1	mistral-small-3.1-24b-instruct-2503OpenMistral	1,303	±4	34,136	—
56	▼ 1	gemma-3-4b-itOpenGoogle	1,302	±9	4,195	—
57	▼ 1	qwen2.5-72b-instructOpenAlibaba	1,302	±4	39,632	—
58	▼ 1	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,298	±8	7,216	—
59	▼ 1	llama-3.1-70b-instructOpenMeta	1,294	±4	56,003	—
60	▼ 1	jamba-1.5-largeOpenAI21 Labs	1,289	±7	8,730	—
61	▼ 1	gemma-2-27b-itOpenGoogle	1,288	±3	76,195	—
62	▼ 1	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,287	±10	3,777	—
63	▼ 1	llama-3.1-tulu-3-70bOpenAi2	1,286	±10	2,881	—
64	▼ 1	gemma-2-9b-it-simpoOpenPrinceton	1,279	±7	10,108	—
65	▼ 1	nemotron-4-340b-instructOpenNVIDIA	1,279	±5	19,913	—
66	▼ 1	command-r-plus-08-2024OpenCohere	1,278	±7	9,931	—
67	▼ 1	llama-3-70b-instructOpenMeta	1,277	±3	158,908	—
68	▼ 1	mistral-small-24b-instruct-2501OpenMistral	1,274	±6	14,830	—
69	▼ 1	qwen2.5-coder-32b-instructOpenAlibaba	1,270	±8	5,452	—
70	▼ 1	c4ai-aya-expanse-32bOpenCohere	1,267	±5	27,362	—
71	▼ 1	gemma-2-9b-itOpenGoogle	1,265	±4	54,954	—
72	▼ 1	deepseek-coder-v2OpenDeepSeek	1,265	±6	15,242	—
73	▼ 1	command-r-plusOpenCohere	1,264	±4	78,401	—
74	▼ 1	qwen2-72b-instructOpenAlibaba	1,263	±5	37,688	—
75	▼ 1	phi-4OpenMicrosoft	1,255	±4	24,354	—
76	▼ 1	olmo-2-0325-32b-instructOpenAi2	1,252	±11	3,377	—
77	▼ 1	command-r-08-2024OpenCohere	1,252	±7	10,229	—
78	▼ 1	jamba-1.5-miniOpenAI21 Labs	1,240	±7	8,918	—
79	▼ 1	ministral-8b-2410OpenMistral	1,237	±9	4,833	—
80	▼ 1	qwen1.5-110b-chatOpenAlibaba	1,235	±5	26,679	—
81	▼ 1	qwen1.5-72b-chatOpenAlibaba	1,235	±5	39,689	—
82	▼ 1	mixtral-8x22b-instruct-v0.1OpenMistral	1,231	±4	52,214	—
83	▼ 1	command-rOpenCohere	1,229	±5	54,710	—
84	—	llama-3-8b-instructOpenMeta	1,224	±4	106,055	—
85	▼ 2	c4ai-aya-expanse-8bOpenCohere	1,224	±7	9,922	—
86	▼ 1	llama-3.1-tulu-3-8bOpenAi2	1,222	±11	2,943	—
87	▼ 1	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,215	±11	4,712	—
88	▼ 1	yi-1.5-34b-chatOpen01 AI	1,214	±5	24,417	—
89	▼ 1	llama-3.1-8b-instructOpenMeta	1,212	±4	50,234	—
90	▼ 1	granite-3.1-8b-instructOpenIBM	1,210	±11	3,142	—
91	▼ 1	qwen1.5-32b-chatOpenAlibaba	1,207	±6	22,068	—
92	▼ 1	phi-3-medium-4k-instructOpenMicrosoft	1,199	±5	25,301	—
93	—	mixtral-8x7b-instruct-v0.1OpenMistral	1,199	±4	74,303	—
94	▼ 2	gemma-2-2b-itOpenGoogle	1,199	±4	46,901	—
95	▼ 1	dbrx-instruct-previewOpenDatabricks	1,197	±6	32,760	—
96	▼ 1	qwen1.5-14b-chatOpenAlibaba	1,194	±7	18,066	—
97	▼ 1	internlm2_5-20b-chatOpenInternLM	1,193	±7	10,038	—
98	▼ 1	wizardlm-70bOpenMicrosoft	1,187	±9	8,270	—
99	▼ 1	deepseek-llm-67b-chatOpenDeepSeek	1,186	±11	4,950	—
100	▼ 1	yi-34b-chatOpen01 AI	1,185	±7	15,624	—
101	▼ 1	granite-3.0-8b-instructOpenIBM	1,184	±9	6,727	—
102	▼ 1	openchat-3.5-0106OpenOpenChat · 1 more variant	1,184	±8	12,712	—
103	—	snowflake-arctic-instructOpenSnowflake	1,182	±6	33,272	—
104	▼ 2	granite-3.1-2b-instructOpenIBM	1,181	±11	3,235	—
105	▼ 1	gemma-1.1-7b-itOpenGoogle	1,181	±6	24,327	—
106	▼ 1	tulu-2-dpo-70bOpenAllenAI/UW	1,180	±10	6,579	—
107	▼ 1	openhermes-2.5-mistral-7bOpenNousResearch	1,178	±10	5,026	—
108	▼ 1	vicuna-33bOpenLMSYS	1,175	±6	22,613	—
109	▼ 1	starling-lm-7b-betaOpenNexusflow	1,174	±7	16,190	—
110	▼ 1	phi-3-small-8k-instructOpenMicrosoft	1,173	±6	17,983	—
111	▼ 1	llama-2-70b-chatOpenMeta	1,173	±5	38,767	—
112	▼ 1	starling-lm-7b-alphaOpenUC Berkeley	1,170	±8	10,267	—
113	▼ 1	llama-3.2-3b-instructOpenMeta	1,168	±8	8,043	—
114	▼ 1	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,167	±12	3,792	—
115	▼ 1	llama2-70b-steerlm-chatOpenNVIDIA	1,158	±13	3,605	—
116	▼ 1	granite-3.0-2b-instructOpenIBM	1,157	±8	6,922	—
117	▼ 1	solar-10.7b-instruct-v1.0OpenUpstage AI	1,155	±13	4,187	—
118	▼ 1	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,154	±15	1,685	—
119	—	mpt-30b-chatOpenMosaicML	1,153	±12	2,606	—
120	▼ 2	mistral-7b-instruct-v0.2OpenMistral	1,152	±7	19,603	—
121	▼ 1	wizardlm-13bOpenMicrosoft	1,152	±9	7,122	—
122	▼ 1	falcon-180b-chatOpenTII	1,149	±17	1,312	—
123	▼ 1	qwen1.5-7b-chatOpenAlibaba	1,145	±10	4,782	—
124	▼ 1	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,144	±6	12,415	—
125	▼ 1	llama-2-13b-chatOpenMeta	1,144	±7	19,357	—
126	▼ 1	vicuna-13bOpenLMSYS	1,143	±7	19,539	—
127	▼ 1	qwen-14b-chatOpenAlibaba	1,141	±11	5,004	—
128	▼ 1	codellama-34b-instructOpenMeta	1,138	±9	7,417	—
129	▼ 1	gemma-7b-itOpenGoogle	1,136	±9	9,034	—
130	▼ 1	zephyr-7b-betaOpenHuggingFace	1,133	±9	11,220	—
131	▼ 1	phi-3-mini-128k-instructOpenMicrosoft	1,133	±7	21,024	—
132	▼ 1	phi-3-mini-4k-instructOpenMicrosoft	1,130	±6	20,539	—
133	▼ 1	zephyr-7b-alphaOpenHuggingFace	1,130	±16	1,803	—
134	▼ 1	guanaco-33bOpenUW	1,130	±12	2,955	—
135	▼ 1	stripedhyena-nous-7bOpenTogether AI	1,122	±11	5,214	—
136	▼ 1	codellama-70b-instructOpenMeta	1,120	±18	1,151	—
137	▼ 1	smollm2-1.7b-instructOpenHuggingFace	1,120	±14	2,244	—
138	▼ 1	vicuna-7bOpenLMSYS	1,117	±9	6,972	—
139	▼ 1	gemma-1.1-2b-itOpenGoogle	1,115	±8	11,035	—
140	▼ 1	llama-3.2-1b-instructOpenMeta	1,114	±8	8,166	—
141	▼ 1	mistral-7b-instructOpenMistral	1,112	±9	9,042	—
142	▼ 1	llama-2-7b-chatOpenMeta	1,110	±7	14,272	—
143	—	qwen1.5-4b-chatOpenAlibaba	1,092	±9	7,662	—
144	▼ 2	gemma-2b-itOpenGoogle	1,092	±12	4,817	—
145	▼ 1	olmo-7b-instructOpenAi2	1,076	±11	6,412	—
146	▼ 1	koala-13bOpenUC Berkeley	1,073	±10	6,998	—
147	▼ 1	alpaca-13bOpenStanford	1,069	±11	5,828	—
148	▼ 1	gpt4all-13b-snoozyOpenNomic AI	1,067	±15	1,773	—
149	▼ 1	mpt-7b-chatOpenMosaicML	1,064	±12	3,977	—
150	▼ 1	chatglm3-6bOpenTsinghua	1,058	±12	4,692	—
151	▼ 1	RWKV-4-Raven-14BOpenRWKV	1,044	±11	4,898	—
152	▼ 1	chatglm2-6bOpenTsinghua	1,027	±14	2,683	—
153	▼ 1	oasst-pythia-12bOpenOpenAssistant	1,024	±11	6,343	—
154	▼ 1	chatglm-6bOpenTsinghua	998	±13	4,968	—
155	▼ 1	fastchat-t5-3bOpenLMSYS	993	±12	4,270	—
156	▼ 1	dolly-v2-12bOpenDatabricks	981	±14	3,471	—
157	▼ 1	llama-13bOpenMeta	973	±16	2,441	—
158	▼ 1	stablelm-tuned-alpha-7bOpenStability AI	954	±13	3,325	—

108 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