Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	kimi-k3-maxOpenMoonshot AI	1,489	±5	18,090	—
2	—	glm-5.3-maxOpenZ.ai	1,482	±7	7,668	—
3	▲ 1	glm-5.3-flashOpenZ.ai	1,474	±9	4,672	$0.24
4	▼ 1	glm-5.2-maxOpenZ.ai	1,472	±5	33,966	—
5	—	mimo-v2.5-proOpenXiaomi	1,468	±4	57,649	—
6	—	glm-5.1OpenZ.ai	1,466	±4	45,650	—
7	▲ 1	kimi-k2.6OpenMoonshot AI	1,461	±5	37,568	—
8	▼ 1	deepseek-v4-pro-high-20260813OpenDeepSeek · 1 more variant	1,460	±8	5,557	—
9	▲ 1	deepseek-v4-proOpenDeepSeek	1,458	±4	54,225	—
10	▼ 1	glm-5OpenZ.ai	1,458	±4	27,647	—
11	—	hy3OpenTencent	1,455	±8	6,958	—
12	—	gemma-4-31bOpenGoogle	1,451	±8	5,898	$0.000
13	—	kimi-k2.5-thinkingOpenMoonshot AI	1,451	±3	70,586	—
14	—	minimax-m3OpenMiniMax	1,443	±4	44,829	$0.52
15	—	glm-4.7OpenZ.ai	1,442	±6	11,889	—
16	—	qwen3.5-397b-a17bOpenAlibaba	1,441	±3	73,640	—
17	—	inklingOpenThinking Machines	1,439	±5	22,229	$1.8
18	—	deepseek-v4-flash-high-previewOpenDeepSeek	1,438	±4	48,691	—
19	—	gemma-4-26b-a4bOpenGoogle	1,438	±8	5,813	—
20	—	qwen3.8-27bOpenAlibaba	1,436	±8	6,913	$1.1
21	—	deepseek-v4-flashOpenDeepSeek	1,436	±4	48,950	—
22	—	mimo-v2.5OpenXiaomi	1,434	±4	44,530	—
23	—	kimi-k2.5-instantOpenMoonshot AI	1,431	±7	7,998	—
24	—	kimi-k2-thinking-turboOpenMoonshot AI	1,430	±3	61,122	—
25	▲ 2	muse-glimmerOpenMeta	1,427	±10	3,693	$0.52
26	▼ 1	mistral-medium-3.5OpenMistral	1,427	±7	11,017	$3.0
27	▼ 1	nvidia-nemotron-3-ultra-550b-a55b-nvfp4OpenNVIDIA	1,426	±7	10,700	—
28	—	deepseek-v3.2OpenDeepSeek · 1 more variant	1,425	±4	46,493	—
29	—	deepseek-v3.2-exp-thinkingOpenDeepSeek · 1 more variant	1,425	±7	8,910	—
30	—	glm-4.6OpenZ.ai	1,425	±4	35,068	—
31	—	qwen3-235b-a22b-instruct-2507OpenAlibaba	1,423	±3	95,700	—
32	—	deepseek-r1-0528OpenDeepSeek · 1 more variant	1,421	±6	18,092	—
33	—	kimi-k2-0905-previewOpenMoonshot AI · 1 more variant	1,418	±7	11,569	—
34	▲ 2	deepseek-v3.1-terminus-thinkingOpenDeepSeek · 1 more variant	1,418	±10	3,372	—
35	—	deepseek-v3.1OpenDeepSeek · 1 more variant	1,417	±6	14,609	—
36	▼ 2	qwen3.5-122b-a10bOpenAlibaba	1,417	±4	28,376	—
37	—	minimax-m2.7OpenMiniMax	1,415	±4	65,655	—
38	▲ 1	qwen3-vl-235b-a22b-instructOpenAlibaba	1,414	±7	11,222	—
39	▼ 1	mistral-large-3OpenMistral	1,414	±3	65,587	—
40	—	hunyuan-hy3-previewOpenTencent	1,413	±8	6,611	—
41	—	glm-4.5OpenZ.ai	1,411	±5	23,715	—
42	—	qwen3.5-27bOpenAlibaba	1,408	±4	27,238	—
43	—	Inkling SmallOpenThinking Machines	1,407	±6	15,183	$0.52
44	—	qwen3-235b-a22b-no-thinkingOpenAlibaba	1,402	±5	37,389	—
45	—	longcat-flash-chatOpenMeituan	1,401	±6	11,161	—
46	—	qwen3-235b-a22b-thinking-2507OpenAlibaba	1,400	±7	8,800	—
47	—	qwen3-next-80b-a3b-instructOpenAlibaba	1,399	±5	22,532	—
48	—	deepseek-v3-0324OpenDeepSeek · 1 more variant	1,396	±4	44,795	—
49	—	qwen3.5-35b-a3bOpenAlibaba	1,395	±4	29,065	—
50	—	qwen3-vl-235b-a22b-thinkingOpenAlibaba	1,395	±7	7,785	—
51	—	step-3.5-flashOpenStepFun	1,394	±4	57,212	—
52	—	mimo-v2-flash (non-thinking)OpenXiaomi · 1 more variant	1,392	±4	46,158	—
53	—	minimax-m2.5OpenMiniMax	1,391	±4	40,884	—
54	—	qwen3-coder-480b-a35b-instructOpenAlibaba	1,387	±5	25,092	—
55	—	minimax-m2.1-previewOpenMiniMax	1,384	±5	16,633	—
56	—	qwen3-30b-a3b-instruct-2507OpenAlibaba	1,382	±5	23,224	—
57	—	trinity-large-previewOpen · 1 more variant	1,379	±4	29,771	—
58	—	glm-4.6vOpenZ.ai	1,378	±11	2,762	—
59	—	qwen3-235b-a22bOpenAlibaba	1,375	±5	25,864	—
60	—	glm-4.5-airOpenZ.ai	1,373	±4	30,372	—
61	—	qwen3-next-80b-a3b-thinkingOpenAlibaba	1,369	±6	13,391	—
62	—	glm-4.7-flashOpenZ.ai	1,366	±6	11,514	—
63	—	gemma-3-27b-itOpenGoogle	1,365	±4	46,421	—
64	—	minimax-m1OpenMiniMax	1,364	±4	34,038	—
65	—	nvidia-nemotron-3-super-120b-a12bOpenNVIDIA	1,361	±7	7,458	—
66	—	mistral-small-2506OpenMistral	1,357	±5	17,399	—
67	—	intellect-3Open	1,356	±8	5,284	—
68	▲ 4	nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4OpenNVIDIA	1,355	±9	4,814	—
69	▼ 1	command-a-03-2025OpenCohere	1,354	±3	55,449	—
70	—	glm-4.5vOpenZ.ai	1,353	±8	4,817	—
71	▼ 2	gpt-oss-120bOpenOpenAI	1,352	±4	29,955	$0.26
72	▼ 1	step-3OpenStepFun	1,349	±8	6,277	—
73	—	llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA	1,347	±12	2,549	—
74	—	qwen3-32bOpenAlibaba	1,347	±9	3,926	—
75	—	minimax-m2OpenMiniMax	1,346	±8	6,752	—
76	—	ling-flash-2.0OpenAnt Group	1,344	±7	6,853	—
77	—	nvidia-llama-3.3-nemotron-super-49b-v1.5OpenNVIDIA	1,343	±10	3,316	—
78	New	granite-4.2-30bOpenIBM	1,342	±11	3,275	—
79	▼ 1	gemma-3-12b-itOpenGoogle	1,342	±10	3,829	—
80	▼ 1	qwq-32bOpenAlibaba · 1 more variant	1,336	±4	25,092	—
81	▼ 1	llama-3.1-405b-instruct-bf16OpenMeta	1,335	±4	41,375	—
82	▼ 1	llama-3.1-405b-instruct-fp8OpenMeta	1,333	±4	59,656	—
83	▼ 1	olmo-3.1-32b-instructOpenAi2	1,330	±6	11,460	—
84	—	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,328	±12	2,218	—
85	▼ 2	molmo-2-8bOpenAi2	1,328	±21	792	—
86	▼ 1	qwen3-30b-a3bOpenAlibaba	1,327	±5	26,092	—
87	▼ 1	llama-4-maverick-17b-128e-instructOpenMeta	1,327	±4	39,360	—
88	▼ 1	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,323	±8	6,795	—
89	▼ 1	llama-4-scout-17b-16e-instructOpenMeta	1,321	±5	29,747	—
90	▼ 1	ring-flash-2.0OpenAnt Group	1,321	±7	6,902	—
91	▼ 1	qwen-max-0919OpenAlibaba	1,318	±6	16,478	—
92	▼ 1	llama-3.3-70b-instructOpenMeta	1,317	±4	54,415	—
93	—	gemma-3n-e4b-itOpenGoogle	1,317	±5	22,087	—
94	▼ 2	gpt-oss-20bOpenOpenAI	1,317	±6	10,394	—
95	▼ 1	nvidia-nemotron-3-nano-30b-a3b-bf16OpenNVIDIA	1,314	±6	15,332	—
96	▼ 1	mistral-large-2407OpenMistral · 1 more variant	1,314	±4	45,459	—
97	▼ 1	athene-v2-chatOpen	1,314	±5	24,739	—
98	▼ 1	olmo-3-32b-thinkOpenAi2	1,307	±8	5,683	—
99	▼ 1	athene-70b-0725Open	1,306	±6	19,621	—
100	▼ 1	granite-4.1-8bOpenIBM	1,306	±10	4,028	—
101	▼ 1	gemma-3-4b-itOpenGoogle	1,303	±9	4,171	—
102	▼ 1	mistral-small-3.1-24b-instruct-2503OpenMistral	1,303	±5	32,630	—
103	▼ 1	qwen2.5-72b-instructOpenAlibaba	1,303	±4	39,406	—
104	▼ 1	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,299	±8	7,140	—
105	New	granite-4.2-3bOpenIBM	1,296	±12	3,093	—
106	▼ 2	llama-3.1-70b-instructOpenMeta	1,293	±4	55,240	—
107	▼ 1	jamba-1.5-largeOpen	1,289	±7	8,662	—
108	▼ 3	gemma-2-27b-itOpenGoogle	1,289	±3	75,754	—
109	New	granite-4.2-8bOpenIBM	1,288	±11	3,111	$0.11
110	▼ 3	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,286	±10	3,749	—
111	▼ 3	llama-3.1-tulu-3-70bOpenAi2	1,286	±10	2,846	—
112	▼ 3	olmo-3.1-32b-thinkOpenAi2	1,286	±7	8,116	—
113	▼ 3	ibm-granite-h-smallOpenIBM	1,285	±8	5,535	—
114	▼ 3	gemma-2-9b-it-simpoOpen	1,280	±7	10,072	—
115	▼ 3	nemotron-4-340b-instructOpenNVIDIA	1,277	±5	19,659	—
116	▼ 3	llama-3-70b-instructOpenMeta	1,276	±4	156,876	—
117	▼ 3	command-r-plus-08-2024OpenCohere	1,276	±7	9,866	—
118	▼ 3	mistral-small-24b-instruct-2501OpenMistral	1,274	±6	14,681	—
119	▼ 3	qwen2.5-coder-32b-instructOpenAlibaba	1,270	±8	5,432	—
120	▼ 3	c4ai-aya-expanse-32bOpenCohere	1,267	±5	27,124	—
121	▼ 3	gemma-2-9b-itOpenGoogle	1,267	±4	54,611	—
122	▼ 3	deepseek-coder-v2OpenDeepSeek	1,265	±6	15,147	—
123	▼ 3	qwen2-72b-instructOpenAlibaba	1,261	±5	37,325	—
124	▼ 3	command-r-plusOpenCohere	1,261	±4	77,554	—
125	▼ 3	phi-4OpenMicrosoft	1,256	±5	24,126	—
126	▼ 3	olmo-2-0325-32b-instructOpenAi2	1,251	±11	3,334	—
127	▼ 3	command-r-08-2024OpenCohere	1,250	±7	10,140	—
128	▼ 3	jamba-1.5-miniOpen	1,239	±7	8,858	—
129	▼ 3	ministral-8b-2410OpenMistral	1,237	±9	4,781	—
130	▼ 3	qwen1.5-110b-chatOpenAlibaba	1,234	±6	26,195	—
131	▼ 3	qwen1.5-72b-chatOpenAlibaba	1,233	±5	39,302	—
132	▼ 3	mixtral-8x22b-instruct-v0.1OpenMistral	1,229	±5	51,416	—
133	▼ 3	command-rOpenCohere	1,226	±5	54,036	—
134	▼ 3	llama-3-8b-instructOpenMeta	1,223	±4	104,642	—
135	▼ 3	c4ai-aya-expanse-8bOpenCohere	1,223	±7	9,818	—
136	▼ 3	llama-3.1-tulu-3-8bOpenAi2	1,220	±11	2,896	—
137	▼ 3	yi-1.5-34b-chatOpen	1,212	±5	24,146	—
138	▼ 3	zephyr-orpo-141b-A35b-v0.1Open	1,212	±11	4,652	—
139	▼ 3	llama-3.1-8b-instructOpenMeta	1,211	±4	49,605	—
140	▼ 3	granite-3.1-8b-instructOpenIBM	1,208	±11	3,090	—
141	▼ 3	qwen1.5-32b-chatOpenAlibaba	1,203	±6	21,741	—
142	▼ 3	gemma-2-2b-itOpenGoogle	1,200	±4	46,616	—
143	▼ 3	phi-3-medium-4k-instructOpenMicrosoft	1,197	±5	25,055	—
144	▼ 3	mixtral-8x7b-instruct-v0.1OpenMistral	1,197	±4	73,503	—
145	▼ 3	dbrx-instruct-previewOpen	1,195	±6	32,191	—
146	▼ 3	qwen1.5-14b-chatOpenAlibaba	1,191	±7	17,839	—
147	▼ 3	internlm2_5-20b-chatOpen	1,190	±7	9,901	—
148	▼ 3	deepseek-llm-67b-chatOpenDeepSeek	1,184	±11	4,932	—
149	▼ 3	wizardlm-70bOpenMicrosoft	1,184	±9	8,214	—
150	▼ 3	yi-34b-chatOpen	1,183	±7	15,483	—
151	▼ 3	granite-3.0-8b-instructOpenIBM	1,182	±9	6,638	—
152	▼ 3	openchat-3.5Open · 1 more variant	1,182	±10	7,968	—
153	▼ 3	gemma-1.1-7b-itOpenGoogle	1,182	±6	23,893	—
154	▼ 3	snowflake-arctic-instructOpen	1,179	±6	32,832	—
155	▼ 3	granite-3.1-2b-instructOpenIBM	1,178	±11	3,188	—
156	▼ 3	tulu-2-dpo-70bOpen	1,177	±10	6,535	—
157	▼ 3	openhermes-2.5-mistral-7bOpen	1,175	±10	5,006	—
158	▼ 3	vicuna-33bOpen	1,172	±6	22,479	—
159	▼ 2	starling-lm-7b-betaOpen	1,171	±7	16,056	—
160	▼ 4	phi-3-small-8k-instructOpenMicrosoft	1,171	±6	17,766	—
161	▼ 3	llama-2-70b-chatOpenMeta	1,170	±5	38,492	—
162	▼ 3	starling-lm-7b-alphaOpen	1,167	±8	10,224	—
163	▼ 3	llama-3.2-3b-instructOpenMeta	1,166	±8	7,936	—
164	▼ 3	nous-hermes-2-mixtral-8x7b-dpoOpen	1,164	±12	3,777	—
165	▼ 3	granite-3.0-2b-instructOpenIBM	1,156	±8	6,837	—
166	▼ 3	llama2-70b-steerlm-chatOpenNVIDIA	1,154	±13	3,585	—
167	▼ 3	solar-10.7b-instruct-v1.0Open	1,152	±13	4,155	—
168	▼ 3	dolphin-2.2.1-mistral-7bOpen	1,152	±15	1,679	—
169	▼ 3	mpt-30b-chatOpen	1,150	±12	2,572	—
170	▼ 3	wizardlm-13bOpenMicrosoft	1,149	±9	7,044	—
171	▼ 3	mistral-7b-instruct-v0.2OpenMistral	1,149	±7	19,402	—
172	▼ 3	falcon-180b-chatOpen	1,147	±17	1,295	—
173	▼ 3	qwen1.5-7b-chatOpenAlibaba	1,143	±10	4,737	—
174	▼ 3	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,143	±6	12,297	—
175	▼ 2	llama-2-13b-chatOpenMeta	1,141	±7	19,174	—
176	▼ 4	vicuna-13bOpen	1,141	±7	19,367	—
177	▼ 3	qwen-14b-chatOpenAlibaba	1,139	±11	4,964	—
178	▼ 3	gemma-7b-itOpenGoogle	1,137	±9	8,925	—
179	▼ 3	codellama-34b-instructOpenMeta	1,136	±9	7,366	—
180	▼ 3	zephyr-7b-betaOpen	1,130	±9	11,118	—
181	▼ 3	phi-3-mini-128k-instructOpenMicrosoft	1,129	±7	20,685	—
182	▼ 3	phi-3-mini-4k-instructOpenMicrosoft	1,128	±6	20,118	—
183	▼ 3	guanaco-33bOpen	1,127	±12	2,921	—
184	▼ 3	zephyr-7b-alphaOpen	1,126	±16	1,785	—
185	▼ 3	stripedhyena-nous-7bOpen	1,121	±11	5,182	—
186	▼ 3	codellama-70b-instructOpenMeta	1,119	±18	1,143	—
187	▼ 3	gemma-1.1-2b-itOpenGoogle	1,116	±8	10,854	—
188	▼ 3	vicuna-7bOpen	1,115	±9	6,923	—
189	▼ 3	smollm2-1.7b-instructOpen	1,114	±14	2,199	—
190	▼ 3	llama-3.2-1b-instructOpenMeta	1,111	±8	8,045	—
191	▼ 3	mistral-7b-instructOpenMistral	1,110	±9	8,977	—
192	▼ 3	llama-2-7b-chatOpenMeta	1,107	±7	14,148	—
193	▼ 3	gemma-2b-itOpenGoogle	1,093	±11	4,780	—
194	▼ 3	qwen1.5-4b-chatOpenAlibaba	1,090	±9	7,597	—
195	▼ 3	olmo-7b-instructOpenAi2	1,073	±11	6,328	—
196	▼ 3	koala-13bOpen	1,070	±10	6,965	—
197	▼ 3	alpaca-13bOpen	1,069	±11	5,745	—
198	▼ 3	gpt4all-13b-snoozyOpen	1,067	±15	1,743	—
199	▼ 3	mpt-7b-chatOpen	1,063	±12	3,924	—
200	▼ 3	chatglm3-6bOpen	1,056	±12	4,658	—
201	▼ 3	RWKV-4-Raven-14BOpen	1,042	±11	4,845	—
202	▼ 3	chatglm2-6bOpen	1,024	±14	2,658	—
203	▼ 3	oasst-pythia-12bOpen	1,023	±11	6,310	—
204	▼ 3	chatglm-6bOpen	995	±13	4,914	—
205	▼ 3	fastchat-t5-3bOpen	992	±12	4,203	—
206	▼ 3	dolly-v2-12bOpen	982	±13	3,412	—
207	▼ 3	llama-13bOpenMeta	974	±16	2,391	—
208	▼ 3	stablelm-tuned-alpha-7bOpen	953	±13	3,287	—

158 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