Model rankings

Rank	Change	Model	Score	95% interval	Votes	Price $/M
1	—	glm-5.1OpenZ.ai	1,475	±6	15,954	—
2	—	mimo-v2.5-proOpenXiaomi	1,466	±5	23,364	—
3	—	kimi-k2.6OpenMoonshot AI	1,462	±5	22,595	—
4	▲ 1	glm-5OpenZ.ai	1,457	±5	23,145	—
5	▼ 1	deepseek-v4-proOpenDeepSeek · 1 more variant	1,457	±5	25,141	—
6	—	gemma-4-31bOpenGoogle	1,451	±8	5,889	$0.000
7	—	kimi-k2.5-thinkingOpenMoonshot AI	1,450	±4	44,488	—
8	—	qwen3.5-397b-a17bOpenAlibaba	1,444	±4	39,840	—
9	—	glm-4.7OpenZ.ai	1,443	±6	12,121	—
10	—	gemma-4-26b-a4bOpenGoogle	1,438	±8	5,802	—
11	—	deepseek-v4-flash-thinkingOpenDeepSeek · 1 more variant	1,436	±5	24,641	—
12	—	mimo-v2.5OpenXiaomi	1,433	±5	23,774	—
13	—	kimi-k2.5-instantOpenMoonshot AI	1,431	±7	8,173	—
14	—	kimi-k2-thinking-turboOpenMoonshot AI	1,430	±3	61,974	—
15	▲ 1	mistral-medium-3.5OpenMistral	1,429	±7	9,535	$3.0
16	▼ 1	glm-4.6OpenZ.ai	1,426	±4	35,655	—
17	▲ 1	deepseek-v3.2OpenDeepSeek · 1 more variant	1,425	±4	47,227	—
18	▼ 1	deepseek-v3.2-exp-thinkingOpenDeepSeek · 1 more variant	1,425	±7	9,068	—
19	—	qwen3-235b-a22b-instruct-2507OpenAlibaba	1,423	±3	97,144	—
20	—	deepseek-r1-0528OpenDeepSeek · 1 more variant	1,422	±6	18,468	—
21	—	nvidia-nemotron-3-ultra-550b-a55b-nvfp4OpenNVIDIA	1,418	±10	3,530	—
22	—	kimi-k2-0905-previewOpenMoonshot AI · 1 more variant	1,418	±6	11,778	—
23	▲ 1	deepseek-v3.1-terminus-thinkingOpenDeepSeek · 1 more variant	1,418	±10	3,465	—
24	▼ 1	deepseek-v3.1OpenDeepSeek · 1 more variant	1,418	±6	14,960	—
25	—	qwen3.5-122b-a10bOpenAlibaba	1,417	±4	28,441	—
26	▲ 2	minimax-m2.7OpenMiniMax	1,416	±5	31,351	—
27	—	mistral-large-3OpenMistral	1,416	±4	43,471	—
28	▼ 2	qwen3-vl-235b-a22b-instructOpenAlibaba	1,415	±6	11,503	—
29	—	hunyuan-hy3-previewOpenTencent	1,414	±8	6,615	—
30	—	glm-4.5OpenZ.ai	1,411	±5	24,311	—
31	—	qwen3.5-27bOpenAlibaba	1,409	±4	27,301	—
32	—	qwen3-235b-a22b-no-thinkingOpenAlibaba	1,403	±5	38,210	—
33	—	qwen3-next-80b-a3b-instructOpenAlibaba	1,402	±5	22,879	—
34	—	longcat-flash-chatOpenMeituan	1,401	±6	11,399	—
35	—	qwen3-235b-a22b-thinking-2507OpenAlibaba	1,399	±7	8,991	—
36	▲ 3	step-3.5-flashOpenStepFun	1,396	±4	41,780	—
37	▼ 1	qwen3.5-35b-a3bOpenAlibaba	1,396	±4	29,123	—
38	▼ 1	qwen3-vl-235b-a22b-thinkingOpenAlibaba	1,396	±7	7,938	—
39	▼ 1	deepseek-v3-0324OpenDeepSeek · 1 more variant	1,395	±4	45,498	—
40	—	mimo-v2-flash (non-thinking)OpenXiaomi · 1 more variant	1,393	±4	46,565	—
41	—	minimax-m2.5OpenMiniMax	1,390	±4	41,149	—
42	—	qwen3-coder-480b-a35b-instructOpenAlibaba	1,387	±5	25,731	—
43	—	minimax-m2.1-previewOpenMiniMax	1,385	±5	17,137	—
44	—	qwen3-30b-a3b-instruct-2507OpenAlibaba	1,383	±5	23,730	—
45	—	trinity-large-previewOpen · 1 more variant	1,379	±4	30,022	—
46	—	glm-4.6vOpenZ.ai	1,377	±11	2,805	—
47	—	qwen3-235b-a22bOpenAlibaba	1,375	±5	26,267	—
48	—	glm-4.5-airOpenZ.ai	1,373	±4	31,075	—
49	—	qwen3-next-80b-a3b-thinkingOpenAlibaba	1,370	±6	13,696	—
50	—	glm-4.7-flashOpenZ.ai	1,368	±6	11,735	—
51	—	gemma-3-27b-itOpenGoogle	1,366	±4	47,540	—
52	—	minimax-m1OpenMiniMax	1,364	±4	35,195	—
53	—	nvidia-nemotron-3-super-120b-a12bOpenNVIDIA	1,362	±7	7,539	—
54	—	mistral-small-2506OpenMistral	1,357	±5	17,709	—
55	—	intellect-3Open	1,357	±8	5,334	—
56	—	command-a-03-2025OpenCohere	1,354	±3	56,264	—
57	—	glm-4.5vOpenZ.ai	1,353	±8	4,958	—
58	—	gpt-oss-120bOpenOpenAI	1,353	±4	30,644	$0.26
59	—	step-3OpenStepFun	1,348	±7	6,545	—
60	—	llama-3.1-nemotron-ultra-253b-v1OpenNVIDIA	1,347	±12	2,549	—
61	—	qwen3-32bOpenAlibaba	1,347	±9	3,926	—
62	—	ling-flash-2.0OpenAnt Group	1,346	±7	7,010	—
63	—	minimax-m2OpenMiniMax	1,346	±8	6,870	—
64	—	nvidia-llama-3.3-nemotron-super-49b-v1.5OpenNVIDIA	1,343	±10	3,345	—
65	—	gemma-3-12b-itOpenGoogle	1,342	±10	3,829	—
66	—	qwq-32bOpenAlibaba · 1 more variant	1,336	±4	25,392	—
67	—	llama-3.1-405b-instruct-bf16OpenMeta	1,335	±4	41,375	—
68	—	llama-3.1-405b-instruct-fp8OpenMeta	1,333	±4	59,656	—
69	—	olmo-3.1-32b-instructOpenAi2	1,330	±6	12,221	—
70	▲ 1	llama-3.3-nemotron-49b-super-v1OpenNVIDIA	1,328	±12	2,218	—
71	▼ 1	molmo-2-8bOpenAi2	1,328	±21	803	—
72	—	qwen3-30b-a3bOpenAlibaba	1,327	±5	26,485	—
73	—	llama-4-maverick-17b-128e-instructOpenMeta	1,327	±4	39,983	—
74	—	deepseek-v2.5-1210OpenDeepSeek · 1 more variant	1,323	±8	6,795	—
75	—	llama-4-scout-17b-16e-instructOpenMeta	1,323	±5	30,296	—
76	—	ring-flash-2.0OpenAnt Group	1,321	±7	7,144	—
77	▲ 1	llama-3.3-70b-instructOpenMeta	1,318	±3	54,738	—
78	▼ 1	gemma-3n-e4b-itOpenGoogle	1,318	±5	22,592	—
79	—	qwen-max-0919OpenAlibaba	1,318	±6	16,478	—
80	—	gpt-oss-20bOpenOpenAI	1,318	±6	10,632	—
81	—	nvidia-nemotron-3-nano-30b-a3b-bf16OpenNVIDIA	1,316	±6	15,514	—
82	—	athene-v2-chatOpen	1,314	±5	24,739	—
83	—	mistral-large-2407OpenMistral · 1 more variant	1,314	±4	45,459	—
84	—	granite-4.1-8bOpenIBM	1,307	±10	4,032	—
85	—	athene-70b-0725Open	1,306	±6	19,621	—
86	—	olmo-3-32b-thinkOpenAi2	1,305	±8	5,945	—
87	—	mistral-small-3.1-24b-instruct-2503OpenMistral	1,303	±5	33,217	—
88	—	gemma-3-4b-itOpenGoogle	1,303	±9	4,171	—
89	—	qwen2.5-72b-instructOpenAlibaba	1,303	±4	39,406	—
90	—	llama-3.1-nemotron-70b-instructOpenNVIDIA	1,299	±8	7,140	—
91	—	llama-3.1-70b-instructOpenMeta	1,293	±4	55,240	—
92	—	jamba-1.5-largeOpen	1,289	±7	8,662	—
93	—	gemma-2-27b-itOpenGoogle	1,289	±3	75,754	—
94	—	ibm-granite-h-smallOpenIBM	1,287	±8	5,684	—
95	—	llama-3.1-tulu-3-70bOpenAi2	1,286	±10	2,846	—
96	—	llama-3.1-nemotron-51b-instructOpenNVIDIA	1,286	±10	3,749	—
97	—	olmo-3.1-32b-thinkOpenAi2	1,285	±7	8,505	—
98	—	gemma-2-9b-it-simpoOpen	1,280	±7	10,072	—
99	—	nemotron-4-340b-instructOpenNVIDIA	1,276	±5	19,659	—
100	—	llama-3-70b-instructOpenMeta	1,276	±4	156,876	—
101	—	command-r-plus-08-2024OpenCohere	1,276	±7	9,866	—
102	—	mistral-small-24b-instruct-2501OpenMistral	1,274	±6	14,681	—
103	—	qwen2.5-coder-32b-instructOpenAlibaba	1,270	±8	5,432	—
104	—	c4ai-aya-expanse-32bOpenCohere	1,267	±5	27,124	—
105	—	gemma-2-9b-itOpenGoogle	1,266	±4	54,611	—
106	—	deepseek-coder-v2OpenDeepSeek	1,264	±6	15,147	—
107	—	qwen2-72b-instructOpenAlibaba	1,261	±5	37,325	—
108	—	command-r-plusOpenCohere	1,261	±4	77,554	—
109	—	phi-4OpenMicrosoft	1,256	±5	24,126	—
110	—	olmo-2-0325-32b-instructOpenAi2	1,251	±11	3,334	—
111	—	command-r-08-2024OpenCohere	1,249	±7	10,140	—
112	—	jamba-1.5-miniOpen	1,239	±7	8,858	—
113	—	ministral-8b-2410OpenMistral	1,237	±9	4,781	—
114	—	qwen1.5-110b-chatOpenAlibaba	1,233	±6	26,195	—
115	—	qwen1.5-72b-chatOpenAlibaba	1,232	±5	39,302	—
116	—	mixtral-8x22b-instruct-v0.1OpenMistral	1,229	±5	51,416	—
117	—	command-rOpenCohere	1,226	±5	54,036	—
118	—	llama-3-8b-instructOpenMeta	1,223	±4	104,642	—
119	—	c4ai-aya-expanse-8bOpenCohere	1,223	±7	9,818	—
120	—	llama-3.1-tulu-3-8bOpenAi2	1,220	±11	2,896	—
121	—	yi-1.5-34b-chatOpen	1,212	±5	24,146	—
122	—	zephyr-orpo-141b-A35b-v0.1Open	1,212	±11	4,652	—
123	—	llama-3.1-8b-instructOpenMeta	1,211	±4	49,605	—
124	—	granite-3.1-8b-instructOpenIBM	1,208	±11	3,090	—
125	—	qwen1.5-32b-chatOpenAlibaba	1,203	±6	21,741	—
126	—	gemma-2-2b-itOpenGoogle	1,200	±4	46,616	—
127	—	phi-3-medium-4k-instructOpenMicrosoft	1,197	±5	25,055	—
128	—	mixtral-8x7b-instruct-v0.1OpenMistral	1,196	±4	73,503	—
129	—	dbrx-instruct-previewOpen	1,194	±6	32,191	—
130	—	internlm2_5-20b-chatOpen	1,191	±7	9,901	—
131	—	qwen1.5-14b-chatOpenAlibaba	1,190	±7	17,839	—
132	—	wizardlm-70bOpenMicrosoft	1,184	±9	8,214	—
133	—	deepseek-llm-67b-chatOpenDeepSeek	1,184	±11	4,932	—
134	—	yi-34b-chatOpen	1,183	±7	15,483	—
135	—	granite-3.0-8b-instructOpenIBM	1,182	±9	6,638	—
136	—	openchat-3.5Open · 1 more variant	1,182	±10	7,968	—
137	—	gemma-1.1-7b-itOpenGoogle	1,181	±6	23,893	—
138	—	snowflake-arctic-instructOpen	1,179	±6	32,832	—
139	—	granite-3.1-2b-instructOpenIBM	1,178	±11	3,188	—
140	—	tulu-2-dpo-70bOpen	1,177	±10	6,535	—
141	—	openhermes-2.5-mistral-7bOpen	1,175	±10	5,006	—
142	—	vicuna-33bOpen	1,172	±6	22,479	—
143	—	starling-lm-7b-betaOpen	1,171	±7	16,056	—
144	—	phi-3-small-8k-instructOpenMicrosoft	1,170	±6	17,766	—
145	—	llama-2-70b-chatOpenMeta	1,170	±6	38,492	—
146	—	starling-lm-7b-alphaOpen	1,167	±8	10,224	—
147	—	llama-3.2-3b-instructOpenMeta	1,166	±8	7,936	—
148	—	nous-hermes-2-mixtral-8x7b-dpoOpen	1,164	±12	3,777	—
149	—	granite-3.0-2b-instructOpenIBM	1,155	±8	6,837	—
150	—	llama2-70b-steerlm-chatOpenNVIDIA	1,154	±13	3,585	—
151	—	solar-10.7b-instruct-v1.0Open	1,151	±13	4,155	—
152	—	dolphin-2.2.1-mistral-7bOpen	1,151	±15	1,679	—
153	—	mpt-30b-chatOpen	1,149	±12	2,572	—
154	—	mistral-7b-instruct-v0.2OpenMistral	1,149	±7	19,402	—
155	—	wizardlm-13bOpenMicrosoft	1,148	±9	7,044	—
156	—	falcon-180b-chatOpen	1,147	±17	1,295	—
157	—	qwen1.5-7b-chatOpenAlibaba	1,143	±10	4,737	—
158	—	phi-3-mini-4k-instruct-june-2024OpenMicrosoft	1,142	±6	12,297	—
159	—	llama-2-13b-chatOpenMeta	1,141	±7	19,174	—
160	—	vicuna-13bOpen	1,140	±7	19,367	—
161	—	qwen-14b-chatOpenAlibaba	1,138	±11	4,964	—
162	—	gemma-7b-itOpenGoogle	1,136	±9	8,925	—
163	—	codellama-34b-instructOpenMeta	1,136	±9	7,366	—
164	—	zephyr-7b-betaOpen	1,130	±9	11,118	—
165	—	phi-3-mini-128k-instructOpenMicrosoft	1,129	±7	20,685	—
166	—	phi-3-mini-4k-instructOpenMicrosoft	1,127	±6	20,118	—
167	—	guanaco-33bOpen	1,126	±12	2,921	—
168	—	zephyr-7b-alphaOpen	1,126	±16	1,785	—
169	—	stripedhyena-nous-7bOpen	1,120	±11	5,182	—
170	—	codellama-70b-instructOpenMeta	1,118	±18	1,143	—
171	—	gemma-1.1-2b-itOpenGoogle	1,115	±8	10,854	—
172	—	vicuna-7bOpen	1,114	±9	6,923	—
173	—	smollm2-1.7b-instructOpen	1,114	±14	2,199	—
174	—	llama-3.2-1b-instructOpenMeta	1,110	±8	8,045	—
175	—	mistral-7b-instructOpenMistral	1,109	±9	8,977	—
176	—	llama-2-7b-chatOpenMeta	1,107	±7	14,148	—
177	—	gemma-2b-itOpenGoogle	1,092	±11	4,780	—
178	—	qwen1.5-4b-chatOpenAlibaba	1,090	±9	7,597	—
179	—	olmo-7b-instructOpenAi2	1,073	±11	6,328	—
180	—	koala-13bOpen	1,070	±10	6,965	—
181	—	alpaca-13bOpen	1,068	±11	5,745	—
182	—	gpt4all-13b-snoozyOpen	1,066	±15	1,743	—
183	—	mpt-7b-chatOpen	1,062	±12	3,924	—
184	—	chatglm3-6bOpen	1,055	±12	4,658	—
185	—	RWKV-4-Raven-14BOpen	1,041	±11	4,845	—
186	—	chatglm2-6bOpen	1,023	±14	2,658	—
187	—	oasst-pythia-12bOpen	1,022	±11	6,310	—
188	—	chatglm-6bOpen	995	±13	4,914	—
189	—	fastchat-t5-3bOpen	991	±12	4,203	—
190	—	dolly-v2-12bOpen	980	±14	3,412	—
191	—	llama-13bOpenMeta	973	±16	2,391	—
192	—	stablelm-tuned-alpha-7bOpen	952	±13	3,287	—

142 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