Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	kimi-k2-thinking-turboOpenMoonshot AI	1,428	±5	19,526	—
2	—	glm-4.6OpenZ.ai	1,424	±4	27,979	—
3	—	deepseek-v3.2-expOpenDeepSeek · 1 more variant	1,423	±6	11,926	—
4	—	deepseek-v3.2-thinkingOpenDeepSeek · 1 more variant	1,422	±7	9,657	—
5	—	qwen3-235b-a22b-instruct-2507OpenAlibaba	1,421	±4	55,241	—
6	—	kimi-k2-0905-previewOpenMoonshot AI · 1 more variant	1,419	±7	11,873	—
7	—	deepseek-r1-0528OpenDeepSeek · 1 more variant	1,418	±6	19,162	—
8	—	mistral-large-3OpenMistral	1,417	±7	10,299	—
9	—	deepseek-v3.1OpenDeepSeek · 1 more variant	1,417	±6	15,210	—
10	—	deepseek-v3.1-terminusOpenDeepSeek · 1 more variant	1,415	±10	3,733	—
11	—	qwen3-vl-235b-a22b-instructOpenAlibaba	1,414	±7	9,449	—
12	—	glm-4.5OpenZ.ai	1,409	±5	24,723	—
13	—	qwen3-next-80b-a3b-instructOpenAlibaba	1,400	±5	23,005	—
14	—	longcat-flash-chatOpenMeituan	1,400	±6	11,465	—
15	—	qwen3-235b-a22b-no-thinkingOpenAlibaba	1,400	±4	39,231	—
16	—	qwen3-235b-a22b-thinking-2507OpenAlibaba	1,397	±6	9,310	—
17	—	qwen3-vl-235b-a22b-thinkingOpenAlibaba	1,394	±7	7,959	—
18	—	deepseek-v3-0324OpenDeepSeek · 1 more variant	1,392	±4	46,613	—
19	New	mimo-v2-flash (non-thinking)OpenXiaomi	1,388	±12	2,604	—
20	▼ 1	qwen3-coder-480b-a35b-instructOpenAlibaba	1,386	±5	24,124	—
21	▼ 1	qwen3-30b-a3b-instruct-2507OpenAlibaba	1,382	±5	24,105	—
22	▼ 1	qwen3-235b-a22bOpenAlibaba	1,374	±5	27,066	—
23	▼ 1	glm-4.5-airOpenZ.ai	1,370	±4	31,522	—
24	▼ 1	qwen3-next-80b-a3b-thinkingOpenAlibaba	1,367	±6	13,762	—
25	▼ 1	minimax-m1OpenMiniMax	1,366	±4	36,709	—
26	▼ 1	gemma-3-27b-itOpenGoogle	1,364	±4	49,174	—
27	—	intellect-3OpenPrime Intellect	1,355	±8	5,426	—
28	▼ 2	mistral-small-2506OpenMistral	1,355	±5	18,247	—
29	▼ 1	gpt-oss-120bOpenOpenAI	1,353	±4	31,118	$0.26
30	▼ 1	glm-4.5vOpenZ.ai	1,352	±8	4,967	—
31	▼ 1	command-a-03-2025OpenCohere	1,352	±3	57,626	—
32	—	step-3OpenStepFun	1,346	±7	6,611	—
33	▼ 2	ling-flash-2.0OpenAnt Group	1,346	±7	7,120	—
34	▼ 1	minimax-m2OpenMiniMax	1,346	±8	7,084	—
35	▼ 1	llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA	1,346	±12	2,573	—
36	▼ 1	qwen3-32bOpenAlibaba	1,345	±9	3,944	—
37	▼ 1	gemma-3-12b-itOpenGoogle	1,340	±9	3,866	—
38	▼ 1	nvidia-llama-3.3-nemotron-super-49b-v1.5OpenNVIDIA	1,340	±10	3,468	—
39	▼ 1	llama-3.1-405b-instruct-bf16OpenMeta	1,335	±4	41,948	—
40	▼ 1	qwq-32bOpenAlibaba · 1 more variant	1,334	±4	26,194	—
41	▼ 1	llama-3.1-405b-instruct-fp8OpenMeta	1,333	±3	60,273	—
42	▼ 1	llama-4-maverick-17b-128e-instructOpenMeta	1,327	±4	41,081	—
43	▼ 1	qwen3-30b-a3bOpenAlibaba	1,326	±5	27,398	—
44	▼ 1	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,326	±12	2,246	—
45	▼ 1	nvidia-nemotron-3-nano-30b-a3b-bf16OpenNVIDIA	1,323	±9	5,033	—
46	▼ 1	llama-4-scout-17b-16e-instructOpenMeta	1,322	±5	31,060	—
47	▼ 1	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,322	±8	6,877	—
48	▼ 1	ring-flash-2.0OpenAnt Group	1,320	±7	7,246	—
49	▼ 1	llama-3.3-70b-instructOpenMeta	1,319	±3	55,954	—
50	▼ 1	gemma-3n-e4b-itOpenGoogle	1,318	±5	23,417	—
51	▼ 1	gpt-oss-20bOpenOpenAI	1,318	±6	10,825	—
52	▼ 1	qwen-max-0919OpenAlibaba	1,317	±6	16,599	—
53	▼ 1	mistral-large-2407OpenMistral · 1 more variant	1,313	±4	45,968	—
54	▼ 1	athene-v2-chatOpenNexusFlow	1,313	±4	24,880	—
55	—	athene-70b-0725OpenNexusFlow	1,305	±6	19,795	—
56	▼ 2	olmo-3-32b-thinkOpenAi2	1,304	±8	5,976	—
57	▼ 1	mistral-small-3.1-24b-instruct-2503OpenMistral	1,303	±4	34,024	—
58	▼ 1	gemma-3-4b-itOpenGoogle	1,302	±9	4,196	—
59	▼ 1	qwen2.5-72b-instructOpenAlibaba	1,302	±4	39,634	—
60	▼ 1	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,297	±8	7,216	—
61	▼ 1	llama-3.1-70b-instructOpenMeta	1,293	±4	56,002	—
62	▼ 1	jamba-1.5-largeOpenAI21 Labs	1,288	±7	8,730	—
63	▼ 1	ibm-granite-h-smallOpenIBM	1,287	±8	5,686	—
64	▼ 1	gemma-2-27b-itOpenGoogle	1,287	±3	76,196	—
65	▼ 1	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,286	±10	3,777	—
66	▼ 1	llama-3.1-tulu-3-70bOpenAi2	1,286	±10	2,882	—
67	▼ 1	gemma-2-9b-it-simpoOpenPrinceton	1,279	±7	10,108	—
68	▼ 1	nemotron-4-340b-instructOpenNVIDIA	1,277	±5	19,913	—
69	▼ 1	command-r-plus-08-2024OpenCohere	1,277	±7	9,932	—
70	▼ 1	llama-3-70b-instructOpenMeta	1,276	±3	158,907	—
71	▼ 1	mistral-small-24b-instruct-2501OpenMistral	1,274	±6	14,831	—
72	▼ 1	qwen2.5-coder-32b-instructOpenAlibaba	1,269	±8	5,452	—
73	▼ 1	c4ai-aya-expanse-32bOpenCohere	1,267	±5	27,362	—
74	▼ 1	gemma-2-9b-itOpenGoogle	1,265	±4	54,957	—
75	▼ 1	deepseek-coder-v2OpenDeepSeek	1,264	±6	15,242	—
76	▼ 1	command-r-plusOpenCohere	1,263	±4	78,400	—
77	▼ 1	qwen2-72b-instructOpenAlibaba	1,262	±5	37,688	—
78	▼ 1	phi-4OpenMicrosoft	1,255	±4	24,355	—
79	▼ 1	olmo-2-0325-32b-instructOpenAi2	1,252	±11	3,379	—
80	▼ 1	command-r-08-2024OpenCohere	1,251	±7	10,229	—
81	▼ 1	jamba-1.5-miniOpenAI21 Labs	1,239	±7	8,918	—
82	▼ 1	ministral-8b-2410OpenMistral	1,237	±9	4,833	—
83	▼ 1	qwen1.5-110b-chatOpenAlibaba	1,234	±5	26,679	—
84	▼ 1	qwen1.5-72b-chatOpenAlibaba	1,234	±5	39,689	—
85	▼ 1	mixtral-8x22b-instruct-v0.1OpenMistral	1,230	±4	52,214	—
86	▼ 1	command-rOpenCohere	1,228	±5	54,710	—
87	▼ 1	c4ai-aya-expanse-8bOpenCohere	1,223	±7	9,922	—
88	▼ 1	llama-3-8b-instructOpenMeta	1,223	±4	106,055	—
89	▼ 1	llama-3.1-tulu-3-8bOpenAi2	1,222	±11	2,943	—
90	▼ 1	zephyr-orpo-141b-A35b-v0.1OpenHuggingFace	1,214	±11	4,712	—
91	▼ 1	yi-1.5-34b-chatOpen01 AI	1,213	±5	24,417	—
92	▼ 1	llama-3.1-8b-instructOpenMeta	1,211	±4	50,235	—
93	▼ 1	granite-3.1-8b-instructOpenIBM	1,210	±11	3,142	—
94	▼ 1	qwen1.5-32b-chatOpenAlibaba	1,205	±6	22,068	—
95	—	gemma-2-2b-itOpenGoogle	1,198	±4	46,900	—
96	▼ 2	phi-3-medium-4k-instructOpenMicrosoft	1,198	±5	25,301	—
97	▼ 1	mixtral-8x7b-instruct-v0.1OpenMistral	1,198	±4	74,303	—
98	▼ 1	dbrx-instruct-previewOpenDatabricks	1,196	±6	32,760	—
99	▼ 1	qwen1.5-14b-chatOpenAlibaba	1,193	±7	18,066	—
100	▼ 1	internlm2_5-20b-chatOpenInternLM	1,192	±7	10,038	—
101	▼ 1	wizardlm-70bOpenMicrosoft	1,185	±9	8,270	—
102	▼ 1	deepseek-llm-67b-chatOpenDeepSeek	1,184	±12	4,950	—
103	▼ 1	yi-34b-chatOpen01 AI	1,184	±7	15,624	—
104	▼ 1	granite-3.0-8b-instructOpenIBM	1,184	±9	6,727	—
105	▼ 1	openchat-3.5-0106OpenOpenChat · 1 more variant	1,183	±8	12,712	—
106	▼ 1	granite-3.1-2b-instructOpenIBM	1,181	±11	3,236	—
107	▼ 1	snowflake-arctic-instructOpenSnowflake	1,180	±6	33,272	—
108	▼ 1	gemma-1.1-7b-itOpenGoogle	1,180	±6	24,327	—
109	▼ 1	tulu-2-dpo-70bOpenAllenAI/UW	1,179	±10	6,579	—
110	▼ 1	openhermes-2.5-mistral-7bOpenNousResearch	1,176	±10	5,026	—
111	▼ 1	vicuna-33bOpenLMSYS	1,173	±6	22,613	—
112	▼ 1	starling-lm-7b-betaOpenNexusflow	1,173	±7	16,190	—
113	▼ 1	phi-3-small-8k-instructOpenMicrosoft	1,172	±6	17,983	—
114	▼ 1	llama-2-70b-chatOpenMeta	1,171	±5	38,767	—
115	▼ 1	starling-lm-7b-alphaOpenUC Berkeley	1,168	±8	10,267	—
116	▼ 1	llama-3.2-3b-instructOpenMeta	1,167	±8	8,043	—
117	▼ 1	nous-hermes-2-mixtral-8x7b-dpoOpenNousResearch	1,166	±12	3,792	—
118	▼ 1	llama2-70b-steerlm-chatOpenNVIDIA	1,157	±13	3,605	—
119	▼ 1	granite-3.0-2b-instructOpenIBM	1,157	±8	6,922	—
120	▼ 1	solar-10.7b-instruct-v1.0OpenUpstage AI	1,154	±13	4,187	—
121	▼ 1	dolphin-2.2.1-mistral-7bOpenCognitive Computations	1,152	±15	1,685	—
122	▼ 1	mpt-30b-chatOpenMosaicML	1,151	±12	2,606	—
123	▼ 1	mistral-7b-instruct-v0.2OpenMistral	1,151	±7	19,603	—
124	▼ 1	wizardlm-13bOpenMicrosoft	1,150	±9	7,122	—
125	▼ 1	falcon-180b-chatOpenTII	1,147	±17	1,312	—
126	▼ 1	qwen1.5-7b-chatOpenAlibaba	1,144	±10	4,782	—
127	▼ 1	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,143	±6	12,414	—
128	▼ 1	llama-2-13b-chatOpenMeta	1,142	±7	19,357	—
129	▼ 1	vicuna-13bOpenLMSYS	1,142	±7	19,539	—
130	▼ 1	qwen-14b-chatOpenAlibaba	1,139	±11	5,004	—
131	▼ 1	codellama-34b-instructOpenMeta	1,137	±9	7,417	—
132	▼ 1	gemma-7b-itOpenGoogle	1,135	±9	9,034	—
133	▼ 1	zephyr-7b-betaOpenHuggingFace	1,132	±9	11,220	—
134	▼ 1	phi-3-mini-128k-instructOpenMicrosoft	1,131	±7	21,024	—
135	▼ 1	phi-3-mini-4k-instructOpenMicrosoft	1,129	±6	20,539	—
136	▼ 1	zephyr-7b-alphaOpenHuggingFace	1,128	±16	1,803	—
137	▼ 1	guanaco-33bOpenUW	1,128	±12	2,955	—
138	▼ 1	stripedhyena-nous-7bOpenTogether AI	1,121	±11	5,214	—
139	▼ 1	codellama-70b-instructOpenMeta	1,119	±18	1,151	—
140	▼ 1	smollm2-1.7b-instructOpenHuggingFace	1,119	±14	2,244	—
141	▼ 1	vicuna-7bOpenLMSYS	1,115	±9	6,972	—
142	▼ 1	gemma-1.1-2b-itOpenGoogle	1,114	±8	11,035	—
143	▼ 1	llama-3.2-1b-instructOpenMeta	1,113	±8	8,166	—
144	▼ 1	mistral-7b-instructOpenMistral	1,111	±9	9,042	—
145	▼ 1	llama-2-7b-chatOpenMeta	1,109	±7	14,272	—
146	▼ 1	gemma-2b-itOpenGoogle	1,091	±12	4,817	—
147	▼ 1	qwen1.5-4b-chatOpenAlibaba	1,091	±9	7,662	—
148	▼ 1	olmo-7b-instructOpenAi2	1,074	±11	6,412	—
149	▼ 1	koala-13bOpenUC Berkeley	1,071	±10	6,998	—
150	▼ 1	alpaca-13bOpenStanford	1,067	±11	5,828	—
151	▼ 1	gpt4all-13b-snoozyOpenNomic AI	1,066	±15	1,773	—
152	▼ 1	mpt-7b-chatOpenMosaicML	1,062	±12	3,977	—
153	▼ 1	chatglm3-6bOpenTsinghua	1,057	±12	4,692	—
154	▼ 1	RWKV-4-Raven-14BOpenRWKV	1,042	±11	4,898	—
155	▼ 1	chatglm2-6bOpenTsinghua	1,026	±14	2,683	—
156	▼ 1	oasst-pythia-12bOpenOpenAssistant	1,023	±11	6,343	—
157	▼ 1	chatglm-6bOpenTsinghua	996	±13	4,968	—
158	▼ 1	fastchat-t5-3bOpenLMSYS	992	±12	4,270	—
159	▼ 1	dolly-v2-12bOpenDatabricks	980	±14	3,471	—
160	▼ 1	llama-13bOpenMeta	972	±16	2,441	—
161	▼ 1	stablelm-tuned-alpha-7bOpenStability AI	953	±13	3,325	—

111 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