Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	glm-5.1OpenZ.ai	1,470	±7	9,028	—
2	New	deepseek-v4-proOpenDeepSeek · 1 more variant	1,463	±9	4,163	—
3	New	kimi-k2.6OpenMoonshot AI	1,458	±9	4,355	—
4	▼ 2	glm-5OpenZ.ai	1,457	±5	17,733	—
5	▼ 2	gemma-4-31bOpenGoogle	1,451	±8	5,818	$0.000
6	▼ 2	kimi-k2.5-thinkingOpenMoonshot AI	1,449	±4	24,213	—
7	▼ 2	qwen3.5-397b-a17bOpenAlibaba	1,446	±5	19,254	—
8	▼ 2	glm-4.7OpenZ.ai	1,443	±6	12,138	—
9	New	deepseek-v4-flash-thinkingOpenDeepSeek · 1 more variant	1,439	±9	3,607	—
10	▼ 3	gemma-4-26b-a4bOpenGoogle	1,439	±8	5,778	—
11	▼ 3	kimi-k2.5-instantOpenMoonshot AI	1,432	±7	8,205	—
12	▼ 3	kimi-k2-thinking-turboOpenMoonshot AI	1,430	±3	49,631	—
13	▼ 3	glm-4.6OpenZ.ai	1,426	±4	35,711	—
14	▼ 3	deepseek-v3.2-exp-thinkingOpenDeepSeek · 1 more variant	1,425	±7	9,078	—
15	▼ 3	deepseek-v3.2OpenDeepSeek · 1 more variant	1,424	±4	44,738	—
16	▼ 3	qwen3-235b-a22b-instruct-2507OpenAlibaba	1,423	±3	85,263	—
17	▼ 3	deepseek-r1-0528OpenDeepSeek · 1 more variant	1,422	±6	18,474	—
18	▼ 3	qwen3.5-122b-a10bOpenAlibaba	1,418	±5	16,040	—
19	▼ 2	kimi-k2-0905-previewOpenMoonshot AI · 1 more variant	1,418	±6	11,800	—
20	▼ 4	deepseek-v3.1OpenDeepSeek · 1 more variant	1,418	±6	14,992	—
21	▼ 3	deepseek-v3.1-terminus-thinkingOpenDeepSeek · 1 more variant	1,417	±10	3,469	—
22	▼ 3	qwen3-vl-235b-a22b-instructOpenAlibaba	1,416	±6	11,528	—
23	▼ 3	mistral-large-3OpenMistral	1,415	±4	41,361	—
24	▼ 3	glm-4.5OpenZ.ai	1,411	±5	24,352	—
25	▼ 3	qwen3.5-27bOpenAlibaba	1,405	±5	15,682	—
26	▼ 3	minimax-m2.7OpenMiniMax	1,403	±6	10,307	—
27	▼ 3	qwen3-235b-a22b-no-thinkingOpenAlibaba	1,403	±4	38,253	—
28	▼ 2	qwen3-next-80b-a3b-instructOpenAlibaba	1,401	±5	22,907	—
29	▼ 2	longcat-flash-chatOpenMeituan	1,401	±6	11,417	—
30	▼ 5	minimax-m2.5OpenMiniMax	1,399	±5	21,236	—
31	▼ 3	qwen3-235b-a22b-thinking-2507OpenAlibaba	1,399	±7	9,008	—
32	▼ 3	qwen3-vl-235b-a22b-thinkingOpenAlibaba	1,396	±7	7,947	—
33	▼ 3	qwen3.5-35b-a3bOpenAlibaba	1,395	±5	16,250	—
34	▼ 3	deepseek-v3-0324OpenDeepSeek · 1 more variant	1,395	±4	45,546	—
35	▼ 2	mimo-v2-flash (non-thinking)OpenXiaomi · 1 more variant	1,393	±4	33,906	—
36	▼ 4	step-3.5-flashOpenStepFun	1,392	±5	21,987	—
37	▼ 3	qwen3-coder-480b-a35b-instructOpenAlibaba	1,387	±5	25,762	—
38	▼ 3	minimax-m2.1-previewOpenMiniMax	1,385	±5	17,150	—
39	▼ 3	qwen3-30b-a3b-instruct-2507OpenAlibaba	1,383	±5	23,768	—
40	▼ 3	glm-4.6vOpenZ.ai	1,378	±11	2,806	—
41	▼ 2	qwen3-235b-a22bOpenAlibaba	1,375	±5	26,285	—
42	▼ 4	trinity-large-previewOpen	1,375	±5	17,170	—
43	▼ 3	glm-4.5-airOpenZ.ai	1,373	±4	31,136	—
44	▼ 3	qwen3-next-80b-a3b-thinkingOpenAlibaba	1,369	±6	13,718	—
45	▼ 3	glm-4.7-flashOpenZ.ai	1,368	±6	11,769	—
46	▼ 3	gemma-3-27b-itOpenGoogle	1,366	±4	47,577	—
47	▼ 3	minimax-m1OpenMiniMax	1,363	±4	35,252	—
48	▼ 3	nvidia-nemotron-3-super-120b-a12bOpenNVIDIA	1,361	±7	7,408	—
49	▼ 3	mistral-small-2506OpenMistral	1,357	±5	17,722	—
50	▼ 3	intellect-3Open	1,356	±8	5,332	—
51	▼ 3	command-a-03-2025OpenCohere	1,354	±3	56,346	—
52	▼ 3	gpt-oss-120bOpenOpenAI	1,353	±4	30,674	$0.26
53	▼ 3	glm-4.5vOpenZ.ai	1,353	±8	4,968	—
54	▼ 3	step-3OpenStepFun	1,348	±7	6,560	—
55	▼ 3	qwen3-32bOpenAlibaba	1,347	±9	3,926	—
56	▼ 3	llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA	1,347	±12	2,549	—
57	▼ 3	minimax-m2OpenMiniMax	1,346	±8	6,876	—
58	▼ 3	ling-flash-2.0OpenAnt Group	1,346	±7	7,018	—
59	▼ 3	nvidia-llama-3.3-nemotron-super-49b-v1.5OpenNVIDIA	1,343	±10	3,347	—
60	▼ 3	gemma-3-12b-itOpenGoogle	1,342	±10	3,829	—
61	▼ 3	qwq-32bOpenAlibaba · 1 more variant	1,336	±4	25,406	—
62	▼ 3	llama-3.1-405b-instruct-bf16OpenMeta	1,335	±4	41,375	—
63	▼ 3	llama-3.1-405b-instruct-fp8OpenMeta	1,333	±4	59,656	—
64	▼ 3	olmo-3.1-32b-instructOpen	1,331	±6	12,238	—
65	▼ 1	molmo-2-8bOpen	1,328	±21	803	—
66	▼ 4	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,327	±12	2,218	—
67	▼ 4	qwen3-30b-a3bOpenAlibaba	1,327	±5	26,507	—
68	▼ 3	llama-4-maverick-17b-128e-instructOpenMeta	1,327	±4	40,010	—
69	▼ 3	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,323	±8	6,795	—
70	▼ 3	llama-4-scout-17b-16e-instructOpenMeta	1,322	±5	30,319	—
71	▼ 3	ring-flash-2.0OpenAnt Group	1,321	±7	7,158	—
72	▼ 3	llama-3.3-70b-instructOpenMeta	1,318	±3	54,756	—
73	▼ 3	gemma-3n-e4b-itOpenGoogle	1,318	±5	22,616	—
74	▼ 3	qwen-max-0919OpenAlibaba	1,318	±6	16,478	—
75	▼ 3	gpt-oss-20bOpenOpenAI	1,317	±6	10,640	—
76	▼ 3	nvidia-nemotron-3-nano-30b-a3b-bf16OpenNVIDIA	1,317	±6	15,526	—
77	▼ 3	athene-v2-chatOpen	1,314	±5	24,739	—
78	▼ 3	mistral-large-2407OpenMistral · 1 more variant	1,314	±4	45,459	—
79	▼ 3	athene-70b-0725Open	1,306	±6	19,621	—
80	▼ 3	olmo-3-32b-thinkOpen	1,305	±8	5,965	—
81	▼ 3	mistral-small-3.1-24b-instruct-2503OpenMistral	1,303	±5	33,239	—
82	▼ 3	gemma-3-4b-itOpenGoogle	1,303	±9	4,171	—
83	▼ 3	qwen2.5-72b-instructOpenAlibaba	1,302	±4	39,406	—
84	▼ 3	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,299	±8	7,140	—
85	▼ 3	llama-3.1-70b-instructOpenMeta	1,293	±4	55,240	—
86	▼ 3	jamba-1.5-largeOpen	1,288	±7	8,662	—
87	▼ 3	gemma-2-27b-itOpenGoogle	1,288	±3	75,754	—
88	▼ 3	ibm-granite-h-smallOpenIBM	1,287	±8	5,690	—
89	▼ 3	llama-3.1-tulu-3-70bOpen	1,286	±10	2,846	—
90	▼ 3	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,286	±10	3,749	—
91	▼ 3	olmo-3.1-32b-thinkOpen	1,285	±7	8,504	—
92	▼ 3	gemma-2-9b-it-simpoOpen	1,279	±7	10,072	—
93	▼ 3	nemotron-4-340b-instructOpenNVIDIA	1,277	±5	19,659	—
94	▼ 3	command-r-plus-08-2024OpenCohere	1,276	±7	9,866	—
95	▼ 3	llama-3-70b-instructOpenMeta	1,276	±4	156,876	—
96	▼ 3	mistral-small-24b-instruct-2501OpenMistral	1,274	±6	14,681	—
97	▼ 3	qwen2.5-coder-32b-instructOpenAlibaba	1,270	±8	5,432	—
98	▼ 3	c4ai-aya-expanse-32bOpenCohere	1,267	±5	27,124	—
99	▼ 3	gemma-2-9b-itOpenGoogle	1,265	±4	54,611	—
100	▼ 3	deepseek-coder-v2OpenDeepSeek	1,264	±6	15,147	—
101	▼ 2	command-r-plusOpenCohere	1,261	±4	77,554	—
102	▼ 4	qwen2-72b-instructOpenAlibaba	1,261	±5	37,325	—
103	▼ 3	phi-4OpenMicrosoft	1,256	±5	24,126	—
104	▼ 3	olmo-2-0325-32b-instructOpen	1,251	±11	3,334	—
105	▼ 3	command-r-08-2024OpenCohere	1,249	±7	10,140	—
106	▼ 3	jamba-1.5-miniOpen	1,239	±7	8,858	—
107	▼ 3	ministral-8b-2410OpenMistral	1,237	±9	4,781	—
108	▼ 3	qwen1.5-110b-chatOpenAlibaba	1,233	±6	26,195	—
109	▼ 3	qwen1.5-72b-chatOpenAlibaba	1,232	±5	39,302	—
110	▼ 3	mixtral-8x22b-instruct-v0.1OpenMistral	1,229	±5	51,416	—
111	▼ 3	command-rOpenCohere	1,226	±5	54,036	—
112	▼ 3	llama-3-8b-instructOpenMeta	1,223	±4	104,642	—
113	▼ 3	c4ai-aya-expanse-8bOpenCohere	1,223	±7	9,818	—
114	▼ 3	llama-3.1-tulu-3-8bOpen	1,220	±11	2,896	—
115	▼ 3	yi-1.5-34b-chatOpen	1,213	±5	24,146	—
116	▼ 3	zephyr-orpo-141b-A35b-v0.1Open	1,212	±11	4,652	—
117	▼ 3	llama-3.1-8b-instructOpenMeta	1,211	±4	49,605	—
118	▼ 3	granite-3.1-8b-instructOpenIBM	1,208	±11	3,090	—
119	▼ 3	qwen1.5-32b-chatOpenAlibaba	1,203	±6	21,741	—
120	▼ 3	gemma-2-2b-itOpenGoogle	1,199	±4	46,616	—
121	▼ 3	phi-3-medium-4k-instructOpenMicrosoft	1,197	±5	25,055	—
122	▼ 3	mixtral-8x7b-instruct-v0.1OpenMistral	1,196	±4	73,503	—
123	▼ 3	dbrx-instruct-previewOpen	1,194	±6	32,191	—
124	▼ 3	internlm2_5-20b-chatOpen	1,191	±7	9,901	—
125	▼ 3	qwen1.5-14b-chatOpenAlibaba	1,190	±7	17,839	—
126	▼ 3	wizardlm-70bOpenMicrosoft	1,184	±9	8,214	—
127	▼ 3	deepseek-llm-67b-chatOpenDeepSeek	1,184	±12	4,932	—
128	▼ 3	yi-34b-chatOpen	1,183	±7	15,483	—
129	▼ 3	openchat-3.5-0106Open · 1 more variant	1,181	±8	12,637	—
130	▼ 3	granite-3.0-8b-instructOpenIBM	1,181	±9	6,638	—
131	▼ 3	gemma-1.1-7b-itOpenGoogle	1,180	±6	23,893	—
132	▼ 3	snowflake-arctic-instructOpen	1,179	±6	32,832	—
133	▼ 3	granite-3.1-2b-instructOpenIBM	1,178	±11	3,188	—
134	▼ 3	tulu-2-dpo-70bOpen	1,177	±10	6,535	—
135	▼ 3	openhermes-2.5-mistral-7bOpen	1,174	±10	5,006	—
136	▼ 3	vicuna-33bOpen	1,172	±6	22,479	—
137	▼ 3	starling-lm-7b-betaOpen	1,171	±7	16,056	—
138	▼ 3	phi-3-small-8k-instructOpenMicrosoft	1,170	±6	17,766	—
139	▼ 3	llama-2-70b-chatOpenMeta	1,170	±6	38,492	—
140	▼ 3	starling-lm-7b-alphaOpen	1,167	±8	10,224	—
141	▼ 3	llama-3.2-3b-instructOpenMeta	1,166	±8	7,936	—
142	▼ 3	nous-hermes-2-mixtral-8x7b-dpoOpen	1,164	±12	3,777	—
143	▼ 3	granite-3.0-2b-instructOpenIBM	1,155	±8	6,837	—
144	▼ 3	llama2-70b-steerlm-chatOpenNVIDIA	1,154	±13	3,585	—
145	▼ 3	solar-10.7b-instruct-v1.0Open	1,151	±13	4,155	—
146	▼ 3	dolphin-2.2.1-mistral-7bOpen	1,151	±15	1,679	—
147	▼ 3	mpt-30b-chatOpen	1,149	±12	2,572	—
148	▼ 3	mistral-7b-instruct-v0.2OpenMistral	1,149	±7	19,402	—
149	▼ 3	wizardlm-13bOpenMicrosoft	1,148	±9	7,044	—
150	▼ 3	falcon-180b-chatOpen	1,146	±17	1,295	—
151	▼ 3	qwen1.5-7b-chatOpenAlibaba	1,143	±10	4,737	—
152	▼ 3	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,142	±6	12,297	—
153	▼ 3	llama-2-13b-chatOpenMeta	1,141	±7	19,174	—
154	▼ 3	vicuna-13bOpen	1,140	±7	19,367	—
155	▼ 3	qwen-14b-chatOpenAlibaba	1,138	±11	4,964	—
156	▼ 3	gemma-7b-itOpenGoogle	1,136	±10	8,925	—
157	▼ 3	codellama-34b-instructOpenMeta	1,136	±9	7,366	—
158	▼ 3	zephyr-7b-betaOpen	1,130	±9	11,118	—
159	▼ 3	phi-3-mini-128k-instructOpenMicrosoft	1,128	±7	20,685	—
160	▼ 3	phi-3-mini-4k-instructOpenMicrosoft	1,127	±6	20,118	—
161	▼ 3	guanaco-33bOpen	1,126	±12	2,921	—
162	▼ 3	zephyr-7b-alphaOpen	1,126	±16	1,785	—
163	▼ 3	stripedhyena-nous-7bOpen	1,120	±11	5,182	—
164	▼ 3	codellama-70b-instructOpenMeta	1,118	±18	1,143	—
165	▼ 3	gemma-1.1-2b-itOpenGoogle	1,114	±8	10,854	—
166	▼ 3	vicuna-7bOpen	1,114	±9	6,923	—
167	▼ 3	smollm2-1.7b-instructOpen	1,113	±14	2,199	—
168	▼ 3	llama-3.2-1b-instructOpenMeta	1,110	±8	8,045	—
169	▼ 3	mistral-7b-instructOpenMistral	1,109	±9	8,977	—
170	▼ 3	llama-2-7b-chatOpenMeta	1,107	±7	14,148	—
171	▼ 3	gemma-2b-itOpenGoogle	1,091	±12	4,780	—
172	▼ 3	qwen1.5-4b-chatOpenAlibaba	1,089	±9	7,597	—
173	▼ 3	olmo-7b-instructOpen	1,074	±11	6,328	—
174	▼ 3	koala-13bOpen	1,070	±10	6,965	—
175	▼ 3	alpaca-13bOpen	1,067	±12	5,745	—
176	▼ 3	gpt4all-13b-snoozyOpen	1,065	±15	1,743	—
177	▼ 3	mpt-7b-chatOpen	1,061	±12	3,924	—
178	▼ 3	chatglm3-6bOpen	1,055	±12	4,658	—
179	▼ 3	RWKV-4-Raven-14BOpen	1,040	±11	4,845	—
180	▼ 3	chatglm2-6bOpen	1,023	±14	2,658	—
181	▼ 3	oasst-pythia-12bOpen	1,021	±11	6,310	—
182	▼ 3	chatglm-6bOpen	995	±13	4,914	—
183	▼ 3	fastchat-t5-3bOpen	991	±12	4,203	—
184	▼ 3	dolly-v2-12bOpen	979	±14	3,412	—
185	▼ 3	llama-13bOpenMeta	972	±16	2,391	—
186	▼ 3	stablelm-tuned-alpha-7bOpen	952	±13	3,287	—

136 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