Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Claude Opus 5.5 (Max, Default Fallback)ClosedAnthropic · 4 more variants	57.6	$8.0	96	653 s
2	—	Claude Sonnet 5.5 (Max, Default Fallback)ClosedAnthropic · 4 more variants	56.0	$4.0	134	372 s
3	—	Muse Wonder Full (Max)ClosedMeta	55.8	—	—	—
4	New	Kimi K3.1 ProClosedKimi	55.1	$4.0	58	3.1 s
5	▼ 1	Claude Fable 5.1 (Max, Default Fallback)ClosedAnthropic · 4 more variants	53.4	$20	70	181 s
6	▼ 1	GPT-6 Astra (Max)ClosedOpenAI · 4 more variants	52.7	$20	66	278 s
7	▼ 1	Gemini 4 Argon (High)ClosedGoogle	52.6	$4.0	81	57 s
8	▼ 1	Muse Wonder (Max)ClosedMeta	52.4	$8.0	162	28 s
9	▼ 1	GPT-6.1 Sol (Max)ClosedOpenAI · 4 more variants	51.8	$4.0	59	236 s
10	—	Grok 4.7 (Xhigh)ClosedSpaceXAI · 2 more variants	46.4	$3.0	93	40 s
11	—	MiMo-V2.6-ProOpenXiaomi	46.3	$0.54	57	3.1 s
12	—	Qwen3.8 Max (0902)ClosedAlibaba	45.4	$3.0	40	2.8 s
13	▲ 10	DeepSeek V4.1 Flash 1017 (Max)OpenDeepSeek	45.1	$0.52	169	1.2 s
14	▼ 1	GLM-5.3 (Max)OpenZ AI · 1 more variant	44.8	$2.2	98	2.4 s
15	▲ 4	Ling 3.1 Flash 1019ClosedInclusionAI · 1 more variant	43.9	$0.45	—	—
16	▼ 2	Step 5 PreviewOpenStepFun	43.7	$1.4	229	1.2 s
17	▼ 1	Claude Haiku 5.5 (Max)ClosedAnthropic · 4 more variants	43.4	$0.20	234	322 s
18	New	MiniMax-M3.1-FlashClosedMiniMax	42.7	$0.26	113	1.4 s
19	▼ 2	GPT-5.6 Terra (Max)ClosedOpenAI · 5 more variants	42.1	$4.5	130	103 s
20	▼ 2	GLM-5.3-FlashOpenZ AI	41.8	$0.24	70	2.8 s
21	▼ 1	Gemini 3.8 Flash (High)ClosedGoogle · 2 more variants	40.9	$1.5	137	27 s
22	▼ 1	Qwen3.8 2.4T A95BOpenAlibaba	39.9	$3.0	41	2.9 s
23	▼ 1	Qwen3.8-Flash-NextOpenAlibaba	39.8	$0.23	52	2.1 s
24	—	Muse Spark Open (Xhigh)OpenMeta	38.9	$2.0	151	0.8 s
25	—	Mistral Large 4 PreviewClosedMistral	38.4	$2.1	109	1.8 s
26	—	GPT-6 Luna (Max)ClosedOpenAI · 5 more variants	38.1	$0.20	140	78 s
27	—	MiMo-V2.6-FlashOpenXiaomi	37.9	$0.18	56	3.8 s
28	—	DeepSeek V4 Pro 0813 (Max)OpenDeepSeek · 1 more variant	36.0	$2.0	105	1.8 s
29	—	Agnes 2.5 Pro BetaClosedSapiens AI	35.2	$0.15	114	1.4 s
30	—	DeepSeek V4 Flash Vision (Max)ClosedDeepSeek	34.8	$0.66	177	1.6 s
31	—	JT-4.1 Flash 236B A21B (Reasoning)ClosedChina Mobile · 1 more variant	33.9	—	—	—
32	—	Qwen3.8 27B (Xhigh)OpenAlibaba · 3 more variants	33.7	$1.1	45	3.9 s
33	—	Motif 3OpenMotif Technologies	33.6	—	—	—
34	—	GPT-5.3 Codex (Xhigh)ClosedOpenAI	32.5	$4.8	99	55 s
35	—	K2 Horizon 375B A23BOpenInstitute of Foundation Models	30.5	$0.000	879	2.2 s
36	—	Beam 1.0OpenReflection	30.3	$0.60	363	0.7 s
37	—	Gemini 3.1 Pro PreviewClosedGoogle	29.7	$4.5	132	21 s
38	—	MiniMax-M3OpenMiniMax	29.2	$0.52	103	1.3 s
39	—	Nex-N2-Pro (Based on Qwen3.5-397B-A17B)OpenNex AGI	28.2	—	—	—
40	—	Quasar 438B (Max, Based on GLM-5.2)ClosedMultiverse Computing	26.7	$0.17	159	1.2 s
41	—	Solar Pro 4ClosedUpstage	26.6	$0.52	—	—
42	—	Nemotron 3.5 Super VLOpenNVIDIA	26.5	$0.31	446	0.7 s
43	—	Apodex 1.1ClosedApodex	26.4	$0.98	—	—
44	—	GPT-5.5 Instant (June 2026)ClosedOpenAI	26.0	$11	152	0.9 s
45	—	Kimi K2.7 CodeOpenKimi	25.8	$1.7	64	2.8 s
46	—	Inkling SmallOpenThinking Machines	25.7	$0.52	223	1.6 s
47	—	K2 Horizon MoVA 36B A4BOpenInstitute of Foundation Models	25.3	—	—	—
48	—	Hy3OpenTencent	25.3	$0.24	81	2.8 s
49	—	Qwen3.7 PlusClosedAlibaba	25.2	$0.70	56	2.3 s
50	—	Inkling (Xhigh)OpenThinking Machines	25.0	$1.8	195	1.8 s
51	—	Solar Open2 250BOpenUpstage	24.7	—	—	—
52	—	Ling-3.0-flash-VLOpenInclusionAI	24.6	—	—	—
53	—	Solar Mini 4ClosedUpstage	24.1	$0.18	112	1.8 s
54	—	Nemotron 3 Ultra 550B A55B (Reasoning)OpenNVIDIA	22.9	$1.1	158	1.2 s
55	—	Ling-3.0-flash-FinOpenInclusionAI	22.6	—	—	—
56	—	Gemini 3.5 Flash-LiteClosedGoogle	22.2	$0.85	414	7.8 s
57	—	G9v3-39A5BOpenAI9Stars	21.8	—	—	—
58	—	KAT Coder Pro V2ClosedKwaiKAT	21.7	—	—	—
59	—	A.X-K2OpenSK Telecom	21.5	—	—	—
60	—	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba · 1 more variant	21.4	$1.4	60	2.1 s
61	—	Nemotron 3.5 Bolt 74B-A9BOpenNVIDIA	21.4	—	—	—
62	—	K2 Horizon 7BOpenInstitute of Foundation Models	20.6	—	—	—
63	—	Qwen3.5 Omni PlusClosedAlibaba	20.4	$1.5	122	2.0 s
64	—	o3ClosedOpenAI	20.2	$3.5	152	7.2 s
65	—	K-EXAONE 2.0 0803OpenLG AI Research	19.7	—	—	—
66	—	LongCat 2.0OpenLongCat	19.1	$1.3	76	2.6 s
67	—	JT-35B-FlashClosedChina Mobile	18.7	—	—	—
68	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	18.2	$0.84	131	2.0 s
69	—	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba · 1 more variant	17.7	$1.1	143	2.3 s
70	—	Muse Glimmer (High)OpenMeta	17.5	$0.52	105	1.1 s
71	—	Doubao Seed CodeClosedByteDance Seed	16.9	—	—	—
72	—	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	16.7	$0.16	91	0.9 s
73	—	Ring-2.6-1TOpenInclusionAI	16.6	$0.85	124	3.7 s
74	—	K2 Horizon 3.7BOpenInstitute of Foundation Models	15.6	—	—	—
75	—	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	14.7	$0.000	35	1.1 s
76	—	ERNIE 5.0 Thinking PreviewClosedBaidu	14.3	—	—	—
77	—	Mistral Medium 3.5OpenMistral	14.2	$3.0	162	2.3 s
78	—	Gemma 4 12B (Reasoning)OpenGoogle · 1 more variant	14.2	$0.15	114	2.2 s
79	—	Nova 2.0 Pro Preview (Medium)ClosedAmazon · 2 more variants	14.2	$3.4	127	13 s
80	—	Nova 2.0 Omni (Medium)ClosedAmazon · 2 more variants	13.6	—	—	—
81	—	Apriel-v1.6-15B-ThinkerOpenServiceNow	13.4	—	—	—
82	—	Nova 2.0 Lite (High)ClosedAmazon · 3 more variants	13.4	$0.85	186	17 s
83	—	Qwen3.5 9B (Non-reasoning)OpenAlibaba · 1 more variant	13.3	$0.19	80	0.9 s
84	—	EXAONE 4.5 33B (Reasoning)OpenLG AI Research	13.2	—	—	—
85	—	Command A+OpenCohere · 1 more variant	13.1	$0.000	166	0.5 s
86	—	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	13.1	$0.060	19	0.9 s
87	—	Nemotron 3.5 LightningOpenNVIDIA	12.9	$0.095	295	0.6 s
88	—	Granite 4.2 30BOpenIBM	12.7	$0.28	47	0.8 s
89	—	Qwen3.5 Omni FlashClosedAlibaba	12.5	$0.28	232	1.8 s
90	—	MiniCPM5-2BOpenOpenBMB	12.5	—	—	—
91	—	Mercury 2.5ClosedInception	12.3	$0.38	714	3.6 s
92	—	JT-MINIClosedChina Mobile	12.2	—	—	—
93	—	Magistral Medium 1.2ClosedMistral	11.8	—	—	—
94	—	HyperNova 60B 2605 (High, Based on gpt-oss-120b)OpenMultiverse Computing	11.7	—	—	—
95	—	Nemotron Cascade 2 30B A3BOpenNVIDIA	11.7	—	—	—
96	—	gpt-oss-120b (High)OpenOpenAI · 1 more variant	11.6	$0.26	233	0.8 s
97	—	K2 Think V2OpenInstitute of Foundation Models	11.5	—	—	—
98	—	LongCat Flash LiteOpenLongCat	11.5	—	—	—
99	—	HyperCLOVA X SEED Think (32B)OpenNaver	11.4	—	—	—
100	—	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	11.3	$0.26	178	0.9 s
101	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	11.2	—	—	—
102	—	Granite 4.2 8BOpenIBM	11.1	$0.11	54	0.8 s
103	—	Ling 3.0 TinyOpenInclusionAI	11.1	$0.000	58	2.6 s
104	—	Mi:dm K 2.5 ProClosedKorea Telecom	11.0	—	—	—
105	—	G9v3-3BOpenAI9Stars	10.8	—	—	—
106	—	Trinity Large ThinkingOpenArcee AI	10.8	$0.39	353	1.3 s
107	—	INTELLECT-3 (Based on GLM-4.5-Air)OpenPrime Intellect	10.6	—	—	—
108	—	Solar Open 100B (Reasoning)OpenUpstage	10.4	—	—	—
109	—	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	10.3	$0.64	231	0.8 s
110	—	gpt-oss-20b (Low)OpenOpenAI · 1 more variant	10.0	$0.13	186	1.0 s
111	—	North Mini CodeOpenCohere	9.9	$0.000	66	0.5 s
112	—	K2-V2 (High)OpenInstitute of Foundation Models · 2 more variants	9.9	—	—	—
113	—	Qwen3 Next 80B A3B InstructOpenAlibaba	9.6	$0.35	133	0.8 s
114	—	DiffusionGemma 26B A4BOpenGoogle	9.5	—	—	—
115	—	Llama 4 MaverickOpenMeta	9.3	$0.42	52	1.0 s
116	—	Qwen3 Coder NextOpenAlibaba	9.2	$0.48	94	0.9 s
117	—	Motif-2-12.7B-ReasoningClosedMotif Technologies	9.2	—	—	—
118	—	Nova PremierClosedAmazon	9.2	—	—	—
119	—	Granite 4.2 3BOpenIBM	9.1	$0.053	51	0.7 s
120	—	Tri-21B-ThinkOpenTrillion Labs	9.0	—	—	—
121	—	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	8.9	$0.040	45	0.9 s
122	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	8.9	$0.088	241	0.9 s
123	—	MiniCPM5-1B (Reasoning)OpenOpenBMB · 1 more variant	8.8	—	—	—
124	—	Sarvam 105B (High)OpenSarvam	8.8	$0.074	189	1.6 s
125	—	Magistral Small 1.2OpenMistral	8.6	$0.75	77	1.5 s
126	—	Nanbeige4.1-3BOpenNanbeige	8.4	—	—	—
127	—	LFM2.5-2.6BOpenLiquid AI	8.4	—	—	—
128	—	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	8.2	—	—	—
129	—	Hermes 4 - Llama-3.1 70B (Reasoning)OpenNous Research · 1 more variant	7.9	—	—	—
130	—	Falcon-H1R-7BOpenTII UAE	7.8	—	—	—
131	—	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	7.8	—	—	—
132	—	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	7.8	$0.43	103	1.9 s
133	—	Step3 VL 10BOpenStepFun	7.7	—	—	—
134	—	Llama 3.3 Instruct 70BOpenMeta	7.7	$0.67	89	1.8 s
135	—	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	7.5	—	—	—
136	—	ERNIE 4.5 300B A47BOpenBaidu	7.5	—	—	—
137	—	Hermes 4 - Llama-3.1 405B (Reasoning)OpenNous Research · 1 more variant	7.5	$1.5	43	2.3 s
138	—	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	7.5	—	—	—
139	—	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	7.4	$0.070	122	0.6 s
140	—	Kimi Linear 48B A3B InstructOpenKimi	7.3	—	—	—
141	—	Llama 3.1 Instruct 405BOpenMeta	7.3	—	—	—
142	—	LFM2.5-8B-A1BOpenLiquid AI	7.2	—	—	—
143	—	Ring-flash-2.0OpenInclusionAI	7.2	—	—	—
144	—	Olmo 3.1 32B ThinkOpenAllen Institute for AI	7.1	—	—	—
145	—	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	6.9	—	—	—
146	—	Sarvam 30B (High)OpenSarvam	6.6	—	—	—
147	—	Olmo 3.1 32B InstructOpenAllen Institute for AI	6.5	—	—	—
148	—	Llama 4 ScoutOpenMeta	6.5	$0.30	118	0.8 s
149	—	R1 1776OpenPerplexity	6.4	—	—	—
150	—	Llama 3.2 Instruct 90B (Vision)OpenMeta	6.4	—	—	—
151	—	Celeris-1ClosedCeleris	6.3	$0.33	1,619	0.6 s
152	—	Phi-4 Mini InstructOpenMicrosoft	6.3	$0.13	46	0.8 s
153	—	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	6.1	—	—	—
154	—	DeepHermes 3 - Mistral 24B Preview (Non-reasoning)OpenNous Research	6.1	—	—	—
155	—	Jamba 1.7 LargeOpenAI21 Labs	6.1	—	—	—
156	—	Granite 4.0 H SmallOpenIBM	6.0	—	—	—
157	—	Ministral 3 14BOpenMistral	6.0	$0.20	77	1.0 s
158	—	Qwen3 Omni 30B A3B InstructOpenAlibaba	6.0	$0.43	96	1.8 s
159	—	LFM2 24B A2BOpenLiquid AI	5.9	—	—	—
160	—	Phi-4OpenMicrosoft	5.9	$0.22	39	2.5 s
161	—	Nova MicroClosedAmazon	5.9	$0.061	290	0.8 s
162	—	Phi-4 Multimodal InstructOpenMicrosoft	5.8	$0.14	—	—
163	—	MiniCPM-V 4.6 1.3BOpenOpenBMB	5.7	—	—	—
164	—	Jamba Reasoning 3BOpenAI21 Labs	5.7	—	—	—
165	—	Reka Flash 3OpenReka AI	5.6	$0.35	88	1.4 s
166	—	Olmo 3 7B ThinkOpenAllen Institute for AI	5.6	—	—	—
167	—	Molmo 7B-DOpenAllen Institute for AI	5.6	—	—	—
168	—	Ministral 3 8BOpenMistral	5.5	$0.15	119	0.9 s
169	—	Llama 3.2 Instruct 11B (Vision)OpenMeta	5.4	$0.35	26	1.3 s
170	—	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	5.3	—	—	—
171	—	Olmo 3 7B InstructOpenAllen Institute for AI	5.2	—	—	—
172	—	LFM2.5-1.2B-ThinkingOpenLiquid AI	5.2	—	—	—
173	—	Jamba 1.7 MiniOpenAI21 Labs	5.2	—	—	—
174	—	LFM2.5-1.2B-InstructOpenLiquid AI	5.2	—	—	—
175	—	Granite 4.0 H 1BOpenIBM	5.2	—	—	—
176	—	Gemma 3 270MOpenGoogle	5.1	—	—	—
177	—	Apertus 70B InstructOpenSwiss AI Initiative	5.1	—	—	—
178	—	Granite 4.0 MicroOpenIBM	5.1	—	—	—
179	—	DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)OpenNous Research	5.1	—	—	—
180	—	Molmo2-8BOpenAllen Institute for AI	5.0	—	—	—
181	—	Ministral 3 3BOpenMistral	4.8	$0.10	209	0.7 s
182	—	Apertus 8B InstructOpenSwiss AI Initiative	4.8	$0.13	136	3.5 s
182	—	Granite 4.0 350MOpenIBM	4.8	—	—	—
182	—	Granite 4.0 H 350MOpenIBM	4.8	—	—	—
182	—	LFM2.5-VL-1.6BOpenLiquid AI	4.8	—	—	—
182	—	Tiny Aya GlobalOpenCohere	4.8	$0.000	—	—
187	—	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	4.8	—	—	—
188	—	K2 Horizon 0.9BOpenInstitute of Foundation Models	3.0	—	—	—

138 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