Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	GPT-5 Codex (high)ClosedOpenAI	68.5	$3.4	—	—
2	—	GPT-5 (high)ClosedOpenAI · 4 more variants	68.5	$3.4	—	—
3	—	o3ClosedOpenAI	65.5	$3.5	—	—
4	—	Grok 4ClosedxAI	65.3	$6.0	—	—
5	—	o3-proClosedOpenAI	65.3	$35	—	—
6	—	GPT-5 mini (high)ClosedOpenAI · 2 more variants	64.3	$0.69	—	—
7	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	62.7	$6.0	—	—
8	—	Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant	60.3	$0.28	—	—
9	—	Gemini 2.5 ProClosedGoogle	59.6	$3.4	—	—
10	—	o4-mini (high)ClosedOpenAI	59.6	$1.9	—	—
11	—	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	59.3	$30	—	—
12	—	gpt-oss-120B (high)OpenOpenAI	58.0	$0.26	—	—
13	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	57.7	$1.9	—	—
14	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	57.5	$2.6	—	—
15	—	Grok 3 mini Reasoning (high)ClosedxAI	57.1	$0.35	—	—
16	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	56.9	$0.32	—	—
17	—	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	56.5	$6.0	—	—
18	—	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	56.0	$0.98	—	—
19	—	Qwen3 MaxClosedAlibaba · 1 more variant	55.2	$2.4	—	—
20	—	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	54.6	$2.0	—	—
21	—	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	54.4	$0.85	—	—
22	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	54.3	$1.9	—	—
23	—	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	54.2	$30	—	—
24	—	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	54.1	$3.4	—	—
25	—	DeepSeek V3.1 (Reasoning)OpenDeepSeek · 1 more variant	54.0	$0.65	—	—
26	—	Magistral Medium 1.2ClosedMistral	52.1	$2.8	—	—
27	—	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	52.0	$1.7	—	—
28	—	Seed-OSS-36B-InstructOpenByteDance Seed	51.6	$0.30	—	—
29	—	Apriel-v1.5-15B-ThinkerOpenServiceNow	51.6	$0.000	—	—
30	—	GLM-4.5 (Reasoning)OpenZ AI	51.3	$0.98	—	—
31	—	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	51.2	$0.85	—	—
32	—	GPT-5 nano (high)ClosedOpenAI · 2 more variants	51.0	$0.14	—	—
33	—	o3-mini (high)ClosedOpenAI · 1 more variant	50.8	$1.9	—	—
34	—	Kimi K2 0905OpenMoonshot AI · 1 more variant	50.4	$1.4	—	—
35	—	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	49.9	$6.0	—	—
36	—	GLM-4.5-AirOpenZ AI	48.8	$0.43	—	—
37	—	Grok Code Fast 1ClosedxAI	48.7	$0.53	—	—
38	—	o1-proClosedOpenAI	48.0	$263	—	—
39	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	47.9	$0.18	—	—
40	—	o1ClosedOpenAI · 1 more variant	47.2	$26	—	—
41	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	46.4	$0.75	—	—
42	—	Sonar Reasoning ProClosedPerplexity	46.3	$0.000	—	—
43	—	MiniMax M1 80kOpenMiniMax	46.2	$0.83	—	—
44	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	45.3	$1.2	—	—
45	—	Grok 3ClosedxAI	45.3	$6.0	—	—
46	—	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	45.2	$0.18	—	—
47	—	Qwen3 Next 80B A3B InstructOpenAlibaba	44.8	$0.88	—	—
48	—	GPT-4.1ClosedOpenAI	43.4	$3.5	—	—
49	—	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	43.4	$0.000	—	—
50	—	gpt-oss-20B (high)OpenOpenAI	43.3	$0.095	—	—
51	—	Magistral Small 1.2OpenMistral	43.0	$0.75	—	—
52	—	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	42.6	$0.70	—	—
53	—	GPT-4.1 miniClosedOpenAI	42.5	$0.70	—	—
54	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	42.3	$3.0	—	—
55	—	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	41.6	$1.5	—	—
56	—	Grok 3 Reasoning BetaClosedxAI	41.4	$0.000	—	—
57	—	DeepSeek V3 0324OpenDeepSeek · 1 more variant	41.3	$0.99	—	—
58	—	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	40.1	$0.18	—	—
59	—	MiniMax M1 40kOpenMiniMax	40.0	$0.83	—	—
60	—	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	40.0	$0.43	—	—
61	—	o1-miniClosedOpenAI	39.2	$1.9	—	—
62	—	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	39.2	$0.20	—	—
63	—	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	38.7	$2.6	—	—
64	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	38.5	$0.90	—	—
65	—	GPT-4.5 (Preview)ClosedOpenAI	38.4	$0.000	—	—
66	—	QwQ 32BOpenAlibaba	37.9	$0.44	—	—
67	—	Solar Pro 2 (Reasoning)ClosedUpstage · 3 more variants	37.7	$0.50	—	—
68	—	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	37.7	$0.000	—	—
69	—	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	37.0	$0.90	—	—
70	—	Qwen3 30B A3B 2507 InstructOpenAlibaba	37.0	$0.35	—	—
71	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	36.9	$0.070	—	—
72	—	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	36.0	$1.3	—	—
73	—	Llama 4 MaverickOpenMeta	35.8	$0.40	—	—
74	—	GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI · 4 more variants	35.6	$7.5	—	—
75	—	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	35.5	$0.000	—	—
76	—	Mistral Medium 3.1ClosedMistral	35.4	$0.80	—	—
77	—	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	34.6	$0.000	—	—
78	—	Sonar ReasoningClosedPerplexity	34.2	$2.0	—	—
79	—	Mistral Medium 3ClosedMistral	33.7	$0.80	—	—
80	—	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	33.6	$0.18	—	—
81	—	Qwen3 Coder 30B A3B InstructOpenAlibaba	33.4	$0.90	—	—
82	—	Magistral Medium 1ClosedMistral	33.2	$2.8	—	—
83	—	ERNIE 4.5 300B A47BOpenBaidu	32.9	$0.49	—	—
84	—	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	32.7	$0.29	—	—
85	—	Nova PremierClosedAmazon	32.3	$5.0	—	—
86	—	Magistral Small 1OpenMistral	31.9	$0.75	—	—
87	—	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	31.0	$0.065	—	—
88	—	Qwen2.5 MaxClosedAlibaba	30.7	$2.8	—	—
89	—	Qwen3 4B 2507 InstructOpenAlibaba	30.4	$0.000	—	—
90	—	Qwen3 Omni 30B A3B InstructOpenAlibaba	30.2	$0.43	—	—
91	—	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	30.0	$0.000	—	—
92	—	DeepSeek R1 Distill Llama 70BOpenDeepSeek	29.9	$0.77	—	—
93	—	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	29.9	$6.0	—	—
94	—	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	29.7	$0.88	—	—
95	—	Mistral Small 3.2OpenMistral	29.1	$0.15	—	—
96	—	Qwen2.5 Instruct 72BOpenAlibaba	29.0	$0.000	—	—
97	—	SonarClosedPerplexity	28.8	$1.0	—	—
98	—	MiniMax-Text-01OpenMiniMax	28.3	$0.43	—	—
99	—	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	28.3	$0.66	—	—
100	—	Sonar ProClosedPerplexity	28.2	$6.0	—	—
101	—	Llama 4 ScoutOpenMeta	28.1	$0.24	—	—
102	—	Llama 3.1 Instruct 405BOpenMeta	28.1	$3.4	—	—
103	—	QwQ 32B-PreviewOpenAlibaba	28.0	$0.67	—	—
104	—	Llama 3.3 Instruct 70BOpenMeta	27.9	$0.54	—	—
105	—	Devstral MediumClosedMistral	27.9	$0.80	—	—
106	—	GPT-4.1 nanoClosedOpenAI	27.3	$0.18	—	—
107	—	Devstral Small (Jul '25)OpenMistral · 1 more variant	27.2	$0.15	—	—
108	—	Qwen3 VL 8B InstructOpenAlibaba	27.1	$0.31	—	—
109	—	Command AOpenCohere	26.9	$4.4	—	—
110	—	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	26.8	$0.13	—	—
111	—	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	26.8	$3.0	—	—
112	—	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	26.7	$0.000	—	—
113	—	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	26.1	$0.000	—	—
114	—	Reka Flash 3OpenReka AI	25.9	$0.35	—	—
115	—	Llama 3.1 Tulu3 405BOpenAllen Institute for AI	25.4	$0.000	—	—
116	—	Nova ProClosedAmazon	25.0	$1.4	—	—
117	—	Pixtral LargeOpenMistral	25.0	$3.0	—	—
118	—	Grok 2 (Dec '24)OpenxAI	24.7	$0.000	—	—
119	—	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	24.4	$0.000	—	—
120	—	GPT-4 TurboClosedOpenAI	24.2	$15	—	—
121	—	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	23.6	$0.60	—	—
122	—	Mistral Small 3.1OpenMistral	23.1	$0.15	—	—
123	—	Grok BetaClosedxAI	23.0	$0.000	—	—
124	—	Qwen2.5 Instruct 32BOpenAlibaba	22.9	$0.000	—	—
125	—	Granite 4.0 H SmallOpenIBM	22.7	$0.11	—	—
126	—	Phi-4OpenMicrosoft Azure	22.7	$0.22	—	—
127	—	Llama 3.1 Instruct 70BOpenMeta	22.6	$0.72	—	—
128	—	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	22.4	$0.40	—	—
129	—	Gemma 3 27B InstructOpenGoogle	22.2	$0.000	—	—
130	—	Qwen2.5 Coder Instruct 32BOpenAlibaba	21.8	$0.20	—	—
131	—	GPT-4ClosedOpenAI	21.5	$38	—	—
132	—	Nova LiteClosedAmazon	21.4	$0.11	—	—
133	—	Mistral Small 3OpenMistral	21.2	$0.15	—	—
134	—	GPT-4o miniClosedOpenAI	21.2	$0.26	—	—
135	—	Jamba Reasoning 3BOpenAI21 Labs	20.9	$0.000	—	—
136	—	Jamba 1.7 LargeOpenAI21 Labs	20.8	$3.5	—	—
137	—	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	20.7	$0.000	—	—
138	—	Claude 3 OpusClosedAnthropic	20.6	$30	—	—
139	—	Gemma 3 12B InstructOpenGoogle	20.4	$0.000	—	—
140	—	Claude 3.5 HaikuClosedAnthropic	20.2	$1.6	—	—
141	—	Codestral (Jan '25)ClosedMistral · 1 more variant	20.2	$0.45	—	—
142	—	Mistral SabaClosedMistral	19.6	$0.30	—	—
143	—	DeepSeek R1 Distill Llama 8BOpenDeepSeek	19.5	$0.000	—	—
144	—	Reka CoreClosedReka AI	19.4	$2.0	—	—
145	—	R1 1776OpenPerplexity	19.1	$3.5	—	—
146	—	Qwen2.5 TurboClosedAlibaba	19.1	$0.088	—	—
147	—	Reka Flash (Sep '24)ClosedReka AI · 1 more variant	19.1	$0.35	—	—
148	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	18.9	$0.72	—	—
148	—	Solar MiniOpenUpstage	18.9	$0.15	—	—
150	—	Reka EdgeClosedReka AI	18.5	$0.10	—	—
151	—	Grok-1OpenxAI	18.2	$0.000	—	—
152	—	Qwen2 Instruct 72BOpenAlibaba	18.1	$0.000	—	—
153	—	Nova MicroClosedAmazon	17.7	$0.061	—	—
154	—	LFM2 8B A1BOpenLiquid AI	17.4	$0.000	—	—
155	—	Gemma 2 27BOpenGoogle	17.2	$0.000	—	—
156	—	Llama 3.1 Instruct 8BOpenMeta	16.9	$0.089	—	—
157	—	Gemini 1.5 Flash-8BClosedGoogle	16.3	$0.000	—	—
158	—	Granite 4.0 MicroOpenIBM	16.2	$0.000	—	—
159	—	Phi-4 Mini InstructOpenMicrosoft Azure	15.7	$0.000	—	—
160	—	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	15.5	$0.000	—	—
161	—	Llama 3.2 Instruct 11B (Vision)OpenMeta	15.5	$0.16	—	—
162	—	Gemma 3n E4B InstructOpenGoogle	15.5	$0.025	—	—
163	—	Granite 3.3 8B (Non-reasoning)OpenIBM	15.2	$0.085	—	—
164	—	Jamba 1.5 LargeOpenAI21 Labs	14.8	$3.5	—	—
165	—	Jamba 1.7 MiniOpenAI21 Labs	14.8	$0.25	—	—
166	—	Gemma 3 4B InstructOpenGoogle	14.7	$0.000	—	—
167	—	Hermes 3 - Llama-3.1 70BOpenNous Research	14.7	$0.30	—	—
168	—	DeepSeek-Coder-V2OpenDeepSeek	14.5	$0.000	—	—
169	—	Phi-3 Medium Instruct 14BOpenMicrosoft Azure	14.4	$0.30	—	—
170	—	Jamba 1.6 LargeOpenAI21 Labs	14.3	$3.5	—	—
171	—	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	14.2	$0.40	—	—
172	—	Aya Expanse 32BOpenCohere	13.6	$0.75	—	—
173	—	Yi-LargeClosed01.AI	13.4	$0.000	—	—
174	—	Claude 3 SonnetClosedAnthropic	13.3	$6.0	—	—
175	—	Llama 3 Instruct 70BOpenMeta	13.0	$0.75	—	—
176	—	Mistral Small (Sep '24)OpenMistral · 1 more variant	13.0	$0.30	—	—
177	—	Gemini 1.0 UltraClosedGoogle	12.8	$0.000	—	—
178	—	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	12.7	$0.23	—	—
179	—	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	12.5	$0.000	—	—
180	—	Phi-4 Multimodal InstructOpenMicrosoft Azure	12.4	$0.000	—	—
181	—	Ministral 8BOpenMistral	12.4	$0.10	—	—
182	—	Qwen2.5 Coder Instruct 7BOpenAlibaba	12.2	$0.000	—	—
183	—	Mistral Large (Feb '24)ClosedMistral	11.9	$6.0	—	—
184	—	Jamba InstructClosedAI21 Labs	11.8	$0.000	—	—
185	—	LFM2 2.6BOpenLiquid AI	11.8	$0.000	—	—
186	—	Mixtral 8x22B InstructOpenMistral	11.7	$3.0	—	—
187	—	Llama 2 Chat 7BOpenMeta	11.3	$0.10	—	—
188	—	Gemma 3n E2B InstructOpenGoogle	11.3	$0.000	—	—
189	—	Llama 3.2 Instruct 3BOpenMeta	11.2	$0.048	—	—
190	—	Ministral 3BClosedMistral	10.9	$0.040	—	—
191	—	Qwen1.5 Chat 110BOpenAlibaba	10.5	$0.000	—	—
192	—	Aya Expanse 8BOpenCohere	10.0	$0.75	—	—
193	—	Claude 2.1ClosedAnthropic	9.7	$0.000	—	—
194	—	Claude 3 HaikuClosedAnthropic	9.6	$0.50	—	—
195	—	Pixtral 12B (2409)OpenMistral	8.9	$0.15	—	—
196	—	Llama 3.2 Instruct 1BOpenMeta	8.9	$0.053	—	—
197	—	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	8.6	$0.000	—	—
198	—	Claude 2.0ClosedAnthropic	8.6	$0.000	—	—
198	—	DeepSeek-V2-ChatOpenDeepSeek	8.6	$0.000	—	—
200	—	Mistral MediumClosedMistral	8.4	$4.1	—	—
201	—	GPT-3.5 TurboClosedOpenAI	8.3	$0.75	—	—
202	—	LFM2 1.2BOpenLiquid AI	8.0	$0.000	—	—
203	—	Gemma 2 9BOpenGoogle	7.8	$0.045	—	—
204	—	Arctic InstructOpenSnowflake	7.6	$0.000	—	—
204	—	Qwen Chat 72BOpenAlibaba	7.6	$1.0	—	—
206	—	LFM 40BClosedLiquid AI	7.3	$0.000	—	—
207	—	Command-R+ (Aug '24)OpenCohere · 3 more variants	7.1	$4.4	—	—
208	—	Llama 3 Instruct 8BOpenMeta	7.0	$0.055	—	—
209	—	Gemma 3 1B InstructOpenGoogle	6.8	$0.000	—	—
210	—	PALM-2ClosedGoogle	6.6	$0.000	—	—
211	—	Gemini 1.0 ProClosedGoogle	6.2	$0.75	—	—
212	—	DeepSeek Coder V2 Lite InstructOpenDeepSeek	6.1	$0.000	—	—
213	—	Gemma 3 270MOpenGoogle	5.6	$0.000	—	—
214	—	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	5.6	$0.000	—	—
214	—	Llama 2 Chat 70BOpenMeta	5.6	$0.000	—	—
216	—	Llama 2 Chat 13BOpenMeta	5.5	$0.000	—	—
217	—	OpenChat 3.5 (1210)OpenOpenChat	5.4	$0.000	—	—
218	—	DBRX InstructOpenDatabricks	5.3	$0.000	—	—
219	—	Mistral NeMoOpenMistral	5.2	$0.15	—	—
220	—	Jamba 1.5 MiniOpenAI21 Labs	4.0	$0.25	—	—
221	—	Jamba 1.6 MiniOpenAI21 Labs	3.3	$0.25	—	—
222	—	Mixtral 8x7B InstructOpenMistral	2.6	$0.70	—	—
223	—	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	1.8	$0.000	—	—
224	—	Claude InstantClosedAnthropic	1.0	$0.000	—	—
224	—	Codestral-MambaOpenMistral	1.0	$0.000	—	—
224	—	Llama 65BOpenMeta	1.0	$0.000	—	—
224	—	Mistral 7B InstructOpenMistral	1.0	$0.25	—	—
224	—	Qwen Chat 14BOpenAlibaba	1.0	$0.000	—	—

178 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