Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	GPT-5.5 (xhigh)ClosedOpenAI	60.2	$11	63	73 s
2	—	GPT-5.5 (high)ClosedOpenAI	58.9	$11	62	24 s
3	—	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic	57.3	$11	43	22 s
4	—	Gemini 3.1 Pro PreviewClosedGoogle	57.2	$4.5	112	29 s
5	—	GPT-5.4 (xhigh)ClosedOpenAI	56.8	$5.6	80	228 s
6	—	GPT-5.5 (medium)ClosedOpenAI	56.7	$11	58	8.2 s
7	—	GPT-5.3 Codex (xhigh)ClosedOpenAI	53.6	$4.8	74	96 s
8	—	Grok 4.3ClosedxAI	53.2	$1.6	72	15 s
9	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic	53.0	$11	40	12 s
10	—	Muse SparkClosedMeta	52.2	—	—	—
11	—	Claude Opus 4.7 (Non-reasoning, High Effort)ClosedAnthropic	51.8	$11	37	1.7 s
12	—	Qwen3.6 Max PreviewClosedAlibaba	51.8	$2.9	36	3.5 s
13	—	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic	51.7	$6.6	51	111 s
14	—	GPT-5.2 (xhigh)ClosedOpenAI	51.3	$4.8	63	156 s
15	—	GPT-5.5 (low)ClosedOpenAI	50.8	$11	58	2.0 s
16	—	Qwen3.6 PlusClosedAlibaba	50.0	$1.1	53	3.1 s
17	—	Claude Opus 4.5 (Reasoning)ClosedAnthropic	49.7	$11	45	9.8 s
18	—	Grok 4.20 0309 v2 (Reasoning)ClosedxAI	49.3	$3.0	87	25 s
19	—	MiMo-V2-ProClosedXiaomi	49.2	$1.5	62	3.2 s
20	—	GPT-5.2 Codex (xhigh)ClosedOpenAI	49.0	$4.8	99	107 s
21	—	GPT-5.4 mini (xhigh)ClosedOpenAI	48.9	$1.7	155	7.9 s
22	—	Grok 4.20 0309 (Reasoning)ClosedxAI	48.5	$3.0	85	28 s
23	—	Gemini 3 Pro Preview (high)ClosedGoogle	48.4	$4.5	126	47 s
24	—	GPT-5.4 (low)ClosedOpenAI	47.9	$5.6	67	2.0 s
25	—	GPT-5.1 (high)ClosedOpenAI	47.7	$3.4	136	25 s
26	—	GLM-5-TurboClosedZ AI	46.8	—	—	—
27	—	GPT-5.2 (medium)ClosedOpenAI	46.6	$4.8	—	—
28	—	Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic	46.5	$11	37	1.7 s
29	—	Gemini 3 Flash Preview (Reasoning)ClosedGoogle	46.4	$1.1	162	6.8 s
30	—	MiMo-V2-Omni-0327ClosedXiaomi	44.9	$0.80	107	2.2 s
31	—	GPT-5 (high)ClosedOpenAI	44.6	$3.4	71	88 s
31	—	GPT-5 Codex (high)ClosedOpenAI	44.6	$3.4	161	9.7 s
33	—	Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic	44.4	$6.6	43	1.4 s
34	—	GPT-5.4 nano (xhigh)ClosedOpenAI	44.0	$0.46	152	4.8 s
35	—	MiMo-V2-OmniClosedXiaomi	43.4	$0.000	110	2.1 s
36	—	GPT-5.1 Codex (high)ClosedOpenAI	43.1	$3.4	167	5.6 s
37	—	Claude Opus 4.5 (Non-reasoning)ClosedAnthropic	43.1	$11	44	1.6 s
38	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic	43.0	$6.6	40	9.1 s
39	—	GLM 5V Turbo (Reasoning)ClosedZ AI	42.9	—	—	—
40	—	Claude Sonnet 4.6 (Non-reasoning, Low Effort)ClosedAnthropic	42.6	$6.6	43	1.2 s
41	—	GPT-5 (medium)ClosedOpenAI	42.0	$3.4	82	41 s
42	—	Claude 4.1 Opus (Reasoning)ClosedAnthropic	42.0	$33	28	12 s
43	—	Grok 4ClosedxAI	41.5	$8.5	42	20 s
44	—	Gemini 3 Pro Preview (low)ClosedGoogle	41.3	$4.5	—	—
45	—	GPT-5 mini (high)ClosedOpenAI	41.2	$0.69	72	106 s
46	—	GPT-5.5 (Non-reasoning)ClosedOpenAI	40.9	$11	56	1.0 s
47	—	o3-proClosedOpenAI	40.7	$35	29	92 s
48	—	Qwen3 Max ThinkingClosedAlibaba	39.9	$2.4	38	3.7 s
49	—	GPT-5 (low)ClosedOpenAI	39.2	$3.4	75	8.5 s
50	—	Claude 4 Opus (Reasoning)ClosedAnthropic	39.0	$33	30	7.6 s
51	—	GPT-5 mini (medium)ClosedOpenAI	38.9	$0.69	73	17 s
52	—	Claude 4 Sonnet (Reasoning)ClosedAnthropic	38.7	$6.6	40	10 s
53	—	GPT-5.1 Codex mini (high)ClosedOpenAI	38.6	$0.69	197	3.6 s
53	—	Qwen3.5 Omni PlusClosedAlibaba	38.6	$1.5	54	2.4 s
55	—	Grok 4.1 Fast (Reasoning)ClosedxAI	38.6	$0.28	78	13 s
56	—	Step 3.5 Flash 2603ClosedStepFun	38.5	$0.000	175	1.0 s
57	—	o3ClosedOpenAI	38.4	$3.5	82	8.3 s
58	—	GPT-5.4 nano (medium)ClosedOpenAI	38.1	$0.46	153	3.1 s
59	—	GPT-5.4 mini (medium)ClosedOpenAI	37.7	$1.7	159	11 s
60	—	Claude 4.5 Sonnet (Non-reasoning)ClosedAnthropic	37.1	$6.6	38	1.6 s
61	—	Claude 4.5 Haiku (Reasoning)ClosedAnthropic	37.1	$2.2	95	13 s
62	—	Claude 4.1 Opus (Non-reasoning)ClosedAnthropic	36.0	$33	29	2.0 s
63	—	Nova 2.0 Pro Preview (medium)ClosedAmazon	35.7	$3.4	143	13 s
64	—	GPT-5.4 (Non-reasoning)ClosedOpenAI	35.4	$5.6	59	0.8 s
65	—	Grok 4 Fast (Reasoning)ClosedxAI	35.1	$0.28	54	9.3 s
66	—	Gemini 3 Flash Preview (Non-reasoning)ClosedGoogle	35.1	$1.1	173	1.1 s
67	—	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic	34.7	—	—	—
68	—	Gemini 2.5 ProClosedGoogle	34.6	$3.4	127	26 s
69	—	Nova 2.0 Lite (high)ClosedAmazon	34.5	$0.85	150	13 s
70	—	GPT-5.2 (Non-reasoning)ClosedOpenAI	33.6	$4.8	60	0.9 s
71	—	Doubao Seed CodeClosedByteDance Seed	33.5	—	—	—
71	—	Gemini 3.1 Flash-Lite PreviewClosedGoogle	33.5	$0.56	326	5.7 s
73	—	o4-mini (high)ClosedOpenAI	33.1	$1.9	123	26 s
74	—	Claude 4 Opus (Non-reasoning)ClosedAnthropic	33.0	$33	30	1.9 s
74	—	Claude 4 Sonnet (Non-reasoning)ClosedAnthropic	33.0	$6.6	39	1.3 s
76	—	Mercury 2ClosedInception	32.8	$0.38	685	3.3 s
77	—	Qwen3 Max Thinking (Preview)ClosedAlibaba	32.5	$2.4	40	4.1 s
78	—	Grok 3 mini Reasoning (high)ClosedxAI	32.1	$0.35	169	0.7 s
79	—	Nova 2.0 Pro Preview (low)ClosedAmazon	31.9	$3.4	140	7.4 s
80	—	Qwen3 MaxClosedAlibaba	31.4	$3.0	32	2.8 s
81	—	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle	31.1	—	—	—
82	—	Claude 4.5 Haiku (Non-reasoning)ClosedAnthropic	31.1	$2.2	86	0.7 s
83	—	Claude 3.7 Sonnet (Non-reasoning)ClosedAnthropic	30.8	$6.6	—	—
84	—	o1ClosedOpenAI	30.8	$26	93	36 s
85	—	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle	30.3	—	—	—
86	—	Nova 2.0 Lite (medium)ClosedAmazon	29.7	$0.85	171	17 s
87	—	Grok 4.20 0309 (Non-reasoning)ClosedxAI	29.7	$3.0	87	0.7 s
88	—	Gemini 2.5 Pro Preview (May' 25)ClosedGoogle	29.5	$3.4	—	—
89	—	ERNIE 5.0 Thinking PreviewClosedBaidu	29.1	—	—	—
90	—	Grok 4.20 0309 v2 (Non-reasoning)ClosedxAI	29.0	$3.0	84	0.7 s
91	—	Grok Code Fast 1ClosedxAI	28.7	$0.53	70	6.4 s
92	—	Nova 2.0 Omni (medium)ClosedAmazon	28.0	$0.85	—	—
93	—	GPT-5.1 (Non-reasoning)ClosedOpenAI	27.4	$3.4	126	1.0 s
94	—	Magistral Medium 1.2ClosedMistral	27.1	$2.8	40	1.6 s
95	—	Gemini 2.5 Flash (Reasoning)ClosedGoogle	27.0	$0.85	219	14 s
96	—	GPT-5 nano (high)ClosedOpenAI	26.8	$0.14	127	101 s
97	—	GPT-4.1ClosedOpenAI	26.3	$3.5	105	1.0 s
98	—	Qwen3 Max (Preview)ClosedAlibaba	26.1	$2.4	51	4.2 s
99	—	GPT-5 nano (medium)ClosedOpenAI	25.9	$0.14	142	42 s
100	—	Qwen3.5 Omni FlashClosedAlibaba	25.9	$0.28	241	1.9 s
100	—	Solar Pro 3ClosedUpstage	25.9	—	—	—
102	—	o3-miniClosedOpenAI	25.9	$1.9	129	8.8 s
103	—	o1-proClosedOpenAI	25.8	$263	—	—
104	—	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)ClosedGoogle	25.7	—	—	—
105	—	JT-MINIClosedChina Mobile	25.4	—	—	—
106	—	o3-mini (high)ClosedOpenAI	25.2	$1.9	133	32 s
107	—	Grok 3ClosedxAI	25.2	$6.0	34	1.8 s
108	—	Sonar Reasoning ProClosedPerplexity	24.6	—	—	—
109	—	Nova 2.0 Lite (low)ClosedAmazon	24.6	$0.85	156	8.3 s
110	—	GPT-5.4 nano (Non-Reasoning)ClosedOpenAI	24.4	$0.46	146	0.6 s
111	—	Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle	24.3	—	—	—
112	—	GPT-5 (minimal)ClosedOpenAI	23.9	$3.4	71	1.7 s
113	—	o1-previewClosedOpenAI	23.7	$29	—	—
114	—	Grok 4.1 Fast (Non-reasoning)ClosedxAI	23.6	$0.28	65	0.7 s
115	—	GPT-5.4 mini (Non-Reasoning)ClosedOpenAI	23.3	$1.7	148	0.6 s
116	—	Nova 2.0 Omni (low)ClosedAmazon	23.2	$0.85	—	—
117	—	Grok 4 Fast (Non-reasoning)ClosedxAI	23.1	$0.28	44	0.7 s
118	—	Mi:dm K 2.5 ProClosedKorea Telecom	23.1	—	—	—
118	—	Nova 2.0 Pro Preview (Non-reasoning)ClosedAmazon	23.1	$3.4	107	1.1 s
120	—	GPT-4.1 miniClosedOpenAI	22.9	$0.70	73	0.8 s
121	—	GPT-5 (ChatGPT)ClosedOpenAI	21.8	$3.4	163	0.8 s
122	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle	21.7	$0.18	—	—
123	—	Grok 3 Reasoning BetaClosedxAI	21.6	—	—	—
124	—	Mistral Medium 3.1ClosedMistral	21.3	$0.80	88	1.5 s
125	—	GPT-5 mini (minimal)ClosedOpenAI	20.7	$0.69	72	1.3 s
126	—	Gemini 2.5 Flash (Non-reasoning)ClosedGoogle	20.6	$0.85	191	0.7 s
127	—	o1-miniClosedOpenAI	20.4	—	—	—
128	—	GPT-4.5 (Preview)ClosedOpenAI	20.0	—	—	—
129	—	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle	19.6	—	—	—
130	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)ClosedGoogle	19.4	$0.18	—	—
131	—	Motif-2-12.7B-ReasoningClosedMotif Technologies	19.1	—	—	—
132	—	Nova PremierClosedAmazon	19.0	$5.0	28	3.1 s
133	—	Solar Pro 2 (Preview) (Reasoning)ClosedUpstage	18.8	—	—	—
134	—	Magistral Medium 1ClosedMistral	18.8	—	—	—
135	—	Mistral Medium 3ClosedMistral	18.8	$0.80	45	1.5 s
136	—	Claude 3.5 HaikuClosedAnthropic	18.7	$1.8	—	—
136	—	Devstral MediumClosedMistral	18.7	$0.80	78	1.4 s
138	—	GPT-4o (Aug '24)ClosedOpenAI	18.6	$4.4	91	1.4 s
139	—	GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI	18.6	—	—	—
140	—	Gemini 2.0 Flash (Feb '25)ClosedGoogle	18.5	$0.26	—	—
141	—	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	18.1	—	—	—
142	—	Nova 2.0 Lite (Non-reasoning)ClosedAmazon	18.0	$0.85	134	1.3 s
143	—	Claude 3 OpusClosedAnthropic	18.0	$33	—	—
144	—	Sonar ReasoningClosedPerplexity	17.9	—	—	—
145	—	Gemini 2.5 Flash Preview (Non-reasoning)ClosedGoogle	17.8	—	—	—
146	—	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle	17.6	$0.18	235	28 s
147	—	GPT-4o (Nov '24)ClosedOpenAI	17.3	$4.4	112	0.9 s
148	—	Gemini 2.0 Flash (experimental)ClosedGoogle	16.8	$0.000	—	—
149	—	Nova 2.0 Omni (Non-reasoning)ClosedAmazon	16.6	$0.85	201	1.4 s
150	—	Qwen2.5 MaxClosedAlibaba	16.3	$2.8	46	3.3 s
151	—	Gemini 1.5 Pro (Sep '24)ClosedGoogle	16.0	—	—	—
151	—	Solar Pro 2 (Preview) (Non-reasoning)ClosedUpstage	16.0	—	—	—
153	—	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic	15.9	$6.6	—	—
154	—	SonarClosedPerplexity	15.5	—	—	—
155	—	Sonar ProClosedPerplexity	15.2	—	—	—
156	—	Solar Pro 2 (Reasoning)ClosedUpstage	14.9	—	—	—
157	—	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle	14.7	—	—	—
158	—	GPT-4o (May '24)ClosedOpenAI	14.5	$7.5	82	1.2 s
159	—	Gemini 2.0 Flash-Lite (Preview)ClosedGoogle	14.5	—	—	—
160	—	Claude 3.5 Sonnet (June '24)ClosedAnthropic	14.2	$6.6	—	—
161	—	GPT-4o (ChatGPT)ClosedOpenAI	14.1	—	—	—
162	—	GPT-5 nano (minimal)ClosedOpenAI	13.8	$0.14	121	1.0 s
163	—	Gemini 1.5 Flash (Sep '24)ClosedGoogle	13.8	—	—	—
164	—	GPT-4 TurboClosedOpenAI	13.7	$15	30	2.9 s
165	—	Solar Pro 2 (Non-reasoning)ClosedUpstage	13.6	—	—	—
166	—	Nova ProClosedAmazon	13.5	$1.4	—	—
167	—	Grok BetaClosedxAI	13.3	—	—	—
168	—	GPT-4.1 nanoClosedOpenAI	13.0	$0.18	122	0.7 s
169	—	GPT-4ClosedOpenAI	12.8	$38	—	—
170	—	Gemini 2.5 Flash-Lite (Non-reasoning)ClosedGoogle	12.7	$0.18	233	1.1 s
171	—	Nova LiteClosedAmazon	12.7	$0.11	164	1.0 s
172	—	GPT-4o miniClosedOpenAI	12.6	$0.26	50	2.7 s
173	—	Gemini 2.0 Flash Thinking Experimental (Dec '24)ClosedGoogle	12.3	—	—	—
174	—	Claude 3 HaikuClosedAnthropic	12.3	$0.50	—	—
175	—	Mistral SabaClosedMistral	12.1	—	—	—
176	—	Gemini 1.5 Pro (May '24)ClosedGoogle	12.0	—	—	—
177	—	Qwen2.5 TurboClosedAlibaba	12.0	$0.088	64	2.4 s
178	—	Reka Flash (Sep '24)ClosedReka AI	12.0	$0.35	58	2.3 s
179	—	Gemini 1.5 Flash-8BClosedGoogle	11.1	—	—	—
180	—	Gemini 1.5 Flash (May '24)ClosedGoogle	10.5	—	—	—
181	—	Claude 3 SonnetClosedAnthropic	10.3	$6.0	—	—
182	—	Nova MicroClosedAmazon	10.3	$0.061	279	0.9 s
183	—	Gemini 1.0 UltraClosedGoogle	10.1	—	—	—
184	—	Mistral Large (Feb '24)ClosedMistral	9.9	$6.0	—	—
185	—	Claude 2.1ClosedAnthropic	9.3	—	—	—
186	—	Claude 2.0ClosedAnthropic	9.1	—	—	—
187	—	Mistral Small (Feb '24)ClosedMistral	9.0	$1.5	128	0.8 s
188	—	Mistral MediumClosedMistral	9.0	$4.1	86	1.5 s
189	—	GPT-3.5 TurboClosedOpenAI	9.0	$0.75	—	—
190	—	LFM 40BClosedLiquid AI	8.8	—	—	—
191	—	PALM-2ClosedGoogle	8.6	—	—	—
192	—	Gemini 1.0 ProClosedGoogle	8.5	—	—	—
193	—	Claude InstantClosedAnthropic	7.4	—	—	—

143 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