Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	GPT-5.5 (xhigh)ClosedOpenAI · 4 more variants	60.2	$11	70	81 s
2	—	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	57.3	$11	66	15 s
3	—	Gemini 3.1 Pro PreviewClosedGoogle	57.2	$4.5	135	33 s
4	—	GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants	56.8	$5.6	84	222 s
5	—	Kimi K2.6OpenKimi · 1 more variant	53.9	$1.7	48	2.9 s
6	—	MiMo-V2.5-ProOpenXiaomi · 1 more variant	53.8	$1.5	56	2.9 s
7	—	GPT-5.3 Codex (xhigh)ClosedOpenAI	53.6	$4.8	80	106 s
8	—	Grok 4.3 (high)ClosedxAI · 1 more variant	53.2	$1.6	83	9.0 s
9	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	52.9	$11	43	19 s
10	—	Muse SparkClosedMeta	52.2	—	—	—
11	—	Qwen3.6 Max PreviewClosedAlibaba	51.8	$2.9	37	4.0 s
12	—	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants	51.7	$6.6	71	115 s
13	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	51.5	$2.2	33	2.0 s
14	—	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	51.4	$2.2	45	1.6 s
15	—	GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants	51.3	$4.8	71	216 s
16	—	Qwen3.6 PlusClosedAlibaba	50.0	$1.1	53	3.0 s
17	—	GLM-5 (Reasoning)OpenZ AI · 1 more variant	49.8	$1.6	91	1.5 s
18	—	Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant	49.7	$11	50	14 s
19	—	MiniMax-M2.7OpenMiniMax	49.6	$0.52	52	2.0 s
20	—	Grok 4.20 0309 v2 (Reasoning)ClosedxAI · 1 more variant	49.3	$3.0	94	29 s
21	—	MiMo-V2-ProClosedXiaomi	49.2	$1.5	73	2.5 s
22	—	GPT-5.2 Codex (xhigh)ClosedOpenAI	49.0	$4.8	107	43 s
23	▼ 1	MiMo-V2.5OpenXiaomi	49.0	$0.72	91	3.2 s
24	—	GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants	48.9	$1.7	165	11 s
25	—	Grok 4.20 0309 (Reasoning)ClosedxAI · 1 more variant	48.5	$3.0	92	30 s
26	—	Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant	48.4	$4.5	141	37 s
27	—	GPT-5.1 (high)ClosedOpenAI · 1 more variant	47.7	$3.4	115	45 s
28	—	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	46.8	$1.1	54	3.1 s
29	—	GLM-5-TurboClosedZ AI	46.8	—	—	—
30	—	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	46.5	$0.18	110	1.2 s
31	—	Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant	46.4	$1.1	170	7.4 s
32	—	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	45.8	$1.4	66	3.8 s
33	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	45.0	$1.4	52	2.5 s
34	—	MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant	44.9	$0.80	107	2.6 s
35	—	GPT-5 Codex (high)ClosedOpenAI	44.6	$3.4	182	9.6 s
36	▼ 1	GPT-5 (high)ClosedOpenAI · 4 more variants	44.6	$3.4	84	79 s
37	—	GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants	44.0	$0.46	145	5.9 s
38	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	43.5	$0.56	203	2.5 s
39	—	GPT-5.1 Codex (high)ClosedOpenAI	43.1	$3.4	181	4.4 s
40	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	43.0	$6.6	44	13 s
41	—	GLM 5V Turbo (Reasoning)ClosedZ AI	42.9	—	—	—
42	—	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	42.1	$1.0	106	1.3 s
43	—	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	42.1	$0.83	87	5.8 s
44	—	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	42.0	$33	35	14 s
45	—	MiniMax-M2.5OpenMiniMax	41.9	$0.52	97	1.8 s
46	—	Hy3-preview (Reasoning)OpenTencent · 1 more variant	41.9	$0.20	116	4.0 s
47	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	41.7	$0.34	—	—
48	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	41.6	$1.1	160	2.5 s
49	—	Grok 4ClosedxAI	41.5	$8.5	45	32 s
50	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	41.5	$0.15	153	2.7 s
51	—	GPT-5 mini (high)ClosedOpenAI · 2 more variants	41.2	$0.69	92	126 s
52	—	Kimi K2 ThinkingOpenKimi	40.9	$1.1	110	2.4 s
53	—	o3-proClosedOpenAI	40.7	$35	29	106 s
54	—	Qwen3 Max ThinkingClosedAlibaba · 1 more variant	39.8	$2.4	47	3.7 s
55	—	MiniMax-M2.1OpenMiniMax	39.4	$0.52	96	1.6 s
56	—	Mistral Medium 3.5OpenMistral	39.2	$3.0	149	1.7 s
57	—	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	39.2	$0.000	35	1.6 s
58	—	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	39.0	$33	37	12 s
59	—	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	38.7	$6.6	46	13 s
60	—	Qwen3.5 Omni PlusClosedAlibaba	38.6	$1.5	54	2.4 s
61	▼ 1	GPT-5.1 Codex mini (high)ClosedOpenAI	38.6	$0.69	200	11 s
62	—	Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant	38.6	$0.28	94	13 s
63	—	Step 3.5 Flash 2603ClosedStepFun · 1 more variant	38.5	$0.000	165	1.2 s
64	—	o3ClosedOpenAI	38.4	$3.5	97	9.3 s
65	—	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	37.1	$0.69	176	2.2 s
66	—	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	37.1	$2.2	96	19 s
67	New	JT-35B-FlashClosedChina Mobile	36.1	—	—	—
68	▼ 1	MiniMax-M2OpenMiniMax	36.1	$0.52	91	1.7 s
69	▼ 1	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	212	1.2 s
70	▼ 1	Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants	35.7	$3.4	123	20 s
71	▼ 1	Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant	35.1	$0.28	102	7.8 s
72	▼ 1	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	34.7	—	—	—
73	▼ 1	Gemini 2.5 ProClosedGoogle	34.6	$3.4	139	24 s
74	▼ 1	Nova 2.0 Lite (high)ClosedAmazon · 3 more variants	34.5	$0.85	125	26 s
75	▼ 1	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	33.9	$1.9	—	—
76	▼ 1	Ling-2.6-1TOpenInclusionAI	33.6	$0.85	—	—
77	▼ 1	Doubao Seed CodeClosedByteDance Seed	33.5	—	—	—
78	▼ 2	Gemini 3.1 Flash-Lite PreviewClosedGoogle	33.5	$0.56	332	6.1 s
79	▼ 1	gpt-oss-120B (high)OpenOpenAI · 1 more variant	33.3	$0.26	260	1.0 s
80	▼ 1	o4-mini (high)ClosedOpenAI	33.1	$1.9	149	36 s
81	▼ 1	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	32.9	$0.31	—	—
82	▼ 1	Mercury 2ClosedInception	32.8	$0.38	905	5.4 s
83	▼ 1	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	32.5	$0.96	45	1.3 s
84	▼ 1	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	32.4	$0.11	64	0.8 s
85	▼ 1	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	32.1	—	—	—
86	▼ 1	Grok 3 mini Reasoning (high)ClosedxAI	32.1	$0.35	158	0.7 s
87	▼ 1	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	109	1.0 s
88	▼ 1	Qwen3 MaxClosedAlibaba · 1 more variant	31.4	$3.0	32	2.3 s
89	▼ 1	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	31.2	$0.20	—	—
90	▼ 1	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	31.1	—	—	—
91	▼ 1	Kimi K2 0905OpenKimi · 1 more variant	30.9	$1.1	16	3.1 s
92	▼ 1	o1ClosedOpenAI · 1 more variant	30.7	$26	98	37 s
93	▼ 1	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	30.3	—	—	—
94	▼ 1	EXAONE 4.5 33BOpenLG AI Research	30.2	—	—	—
95	▼ 1	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	30.1	$0.15	83	1.2 s
96	▼ 1	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	29.5	$0.84	52	2.8 s
97	▼ 1	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
98	▼ 1	ERNIE 5.0 Thinking PreviewClosedBaidu	29.1	—	—	—
99	▼ 1	Grok Code Fast 1ClosedxAI	28.7	$0.53	65	7.9 s
100	▼ 1	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
101	▼ 1	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	145	1.4 s
102	▼ 1	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	28.1	$0.83	—	—
103	▼ 1	Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants	28.0	$0.85	—	—
104	▼ 1	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	27.8	$0.26	153	0.7 s
105	▼ 1	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.2	33	3.1 s
106	▼ 1	Magistral Medium 1.2ClosedMistral	27.1	$2.8	42	1.7 s
107	▼ 1	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	27.1	$0.060	197	0.5 s
108	▼ 1	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	27.1	$2.1	—	—
109	▼ 1	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	27.0	$0.85	212	17 s
110	▼ 1	GPT-5 nano (high)ClosedOpenAI · 2 more variants	26.8	$0.14	148	106 s
111	▼ 1	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	167	2.2 s
112	▼ 1	GLM-4.5 (Reasoning)OpenZ AI	26.4	$1.0	48	3.2 s
113	▼ 1	GPT-4.1ClosedOpenAI	26.3	$3.5	91	1.2 s
114	▼ 1	Ling 2.6 FlashOpenInclusionAI	26.2	$0.15	—	—
115	▼ 1	Solar Pro 3ClosedUpstage	25.9	—	—	—
116	▼ 2	Qwen3.5 Omni FlashClosedAlibaba	25.9	$0.28	266	1.9 s
117	▼ 1	o3-miniClosedOpenAI · 1 more variant	25.9	$1.9	133	8.1 s
118	▼ 1	o1-proClosedOpenAI	25.8	$263	—	—
119	▼ 1	JT-MINIClosedChina Mobile	25.4	—	—	—
120	▼ 1	Grok 3ClosedxAI	25.2	$6.0	30	2.1 s
121	▼ 1	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	34	3.5 s
122	▼ 1	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$0.36	58	2.3 s
123	▼ 1	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$0.68	62	3.0 s
124	▼ 1	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	85	2.8 s
125	▼ 1	Sonar Reasoning ProClosedPerplexity	24.6	—	—	—
126	▼ 1	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.088	241	0.8 s
127	▼ 1	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
128	▼ 1	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.096	109	2.5 s
129	▼ 1	LongCat Flash LiteOpenLongCat	23.9	$0.000	113	7.0 s
130	▼ 1	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	23.4	$0.45	35	3.5 s
131	▼ 1	GLM-4.5-AirOpenZ AI	23.2	$0.37	62	3.2 s
132	▼ 1	Mi:dm K 2.5 ProClosedKorea Telecom	23.1	—	—	—
133	▼ 1	GPT-4.1 miniClosedOpenAI	22.9	$0.70	66	1.0 s
134	▼ 1	Mistral Large 3OpenMistral	22.8	$0.75	50	1.1 s
135	▼ 1	Ring-1TOpenInclusionAI	22.8	—	—	—
136	▼ 1	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.4	$0.67	139	2.5 s
137	▼ 1	DeepSeek V3 0324OpenDeepSeek · 1 more variant	22.3	$1.2	—	—
138	▼ 1	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
139	▼ 1	Devstral 2OpenMistral	22.0	$0.000	56	1.1 s
140	▼ 1	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
141	—	Grok 3 Reasoning BetaClosedxAI	21.6	—	—	—
142	▼ 2	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	21.6	$0.18	—	—
143	▼ 1	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	21.4	$0.13	300	1.0 s
144	▼ 1	Mistral Medium 3.1ClosedMistral	21.3	$0.80	74	1.5 s
145	▼ 1	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
146	▼ 1	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$0.70	48	2.9 s
147	▼ 1	o1-miniClosedOpenAI	20.4	—	—	—
148	▼ 1	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	163	2.2 s
149	▼ 1	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.35	95	2.7 s
150	▼ 1	GPT-4.5 (Preview)ClosedOpenAI	20.0	—	—	—
151	▼ 1	QwQ 32BOpenAlibaba	19.7	$0.75	28	2.1 s
152	▼ 1	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.34	106	2.3 s
153	▼ 1	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	19.6	—	—	—
154	▼ 1	Devstral Small 2OpenMistral	19.5	$0.000	52	1.2 s
155	▼ 1	Motif-2-12.7B-ReasoningClosedMotif Technologies	19.1	—	—	—
156	▼ 1	Ling-1TOpenInclusionAI	19.0	—	—	—
157	▼ 1	Nova PremierClosedAmazon	19.0	$5.0	31	2.9 s
158	▼ 1	Solar Pro 2 (Preview) (Reasoning)ClosedUpstage · 3 more variants	18.8	—	—	—
159	▼ 1	Magistral Medium 1ClosedMistral	18.8	—	—	—
160	▼ 1	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	18.8	—	—	—
161	▼ 2	Mistral Medium 3ClosedMistral	18.8	$0.80	42	1.5 s
162	▼ 1	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	50	1.3 s
163	▼ 1	Claude 3.5 HaikuClosedAnthropic	18.7	$1.8	—	—
164	▼ 2	Devstral MediumClosedMistral	18.7	$0.80	75	1.4 s
165	▼ 1	GPT-4o (Aug '24)ClosedOpenAI · 4 more variants	18.6	$4.4	121	1.0 s
166	▼ 1	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	18.5	$0.26	—	—
167	▼ 1	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
168	▼ 1	Llama 4 MaverickOpenMeta	18.4	$0.48	109	1.1 s
169	▼ 1	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	18.2	—	—	—
170	▼ 1	Magistral Small 1.2OpenMistral	18.2	$0.75	104	0.8 s
171	▼ 2	Sarvam 105B (high)OpenSarvam	18.2	$0.000	116	2.3 s
172	▼ 1	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	18.1	—	—	—
173	▼ 1	Devstral Small (May '25)OpenMistral · 1 more variant	18.0	—	—	—
174	▼ 1	Claude 3 OpusClosedAnthropic	18.0	$33	—	—
175	▼ 1	Sonar ReasoningClosedPerplexity	17.9	—	—	—
176	▼ 1	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	17.6	$0.18	274	29 s
177	▼ 1	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	38	2.4 s
178	▼ 1	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	56	3.0 s
179	▼ 1	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	—	—	—
180	▼ 1	Magistral Small 1OpenMistral	16.8	—	—	—
181	▼ 1	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	16.7	—	—	—
182	▼ 1	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	110	2.5 s
183	▼ 1	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	16.5	$0.28	96	2.5 s
184	▼ 1	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
185	▼ 1	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	16.3	$0.040	—	—
186	▼ 1	Qwen2.5 MaxClosedAlibaba	16.3	$2.8	46	3.4 s
187	▼ 1	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	16.2	$0.73	59	2.8 s
188	▼ 1	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
189	▼ 1	Qwen3 VL 30B A3B InstructOpenAlibaba	16.0	$0.30	106	2.2 s
190	▼ 1	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	16.0	—	—	—
191	▼ 1	Ministral 3 14BOpenMistral	16.0	$0.20	93	0.7 s
192	▼ 1	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	42	1.7 s
193	▼ 1	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	15.9	$6.6	—	—
194	▼ 1	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
195	▼ 1	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
196	▼ 1	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	80	2.5 s
197	▼ 1	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	79	2.0 s
198	▼ 1	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.37	27	3.7 s
199	▼ 1	SonarClosedPerplexity	15.5	—	—	—
200	▼ 1	Step3 VL 10BOpenStepFun	15.5	—	—	—
201	▼ 1	Sonar ProClosedPerplexity	15.2	—	—	—
202	▼ 1	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	15.2	—	—	—
203	▼ 1	QwQ 32B-PreviewOpenAlibaba	15.2	—	—	—
204	▼ 1	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	15.1	$0.90	46	1.9 s
205	▼ 2	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	15.1	$3.0	31	1.8 s
206	▼ 1	Mistral Small 3.2OpenMistral	15.1	$0.13	116	0.7 s
207	▼ 1	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	41	2.6 s
208	▼ 1	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.21	105	2.1 s
209	▼ 1	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	23	3.6 s
210	▼ 1	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	—	—
211	▼ 1	Ministral 3 8BOpenMistral	14.8	$0.15	93	0.7 s
212	▼ 1	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	122	0.6 s
213	▼ 1	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	14.7	—	—	—
214	▼ 1	Granite 4.1 30BOpenIBM	14.7	—	—	—
215	▼ 1	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
216	▼ 1	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.62	75	1.7 s
217	▼ 1	Mistral Small 3.1OpenMistral	14.5	$0.14	142	0.7 s
218	▼ 1	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
219	▼ 1	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
220	▼ 1	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	116	2.3 s
221	▼ 1	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	86	2.6 s
222	▼ 1	Pixtral LargeOpenMistral	14.0	$3.0	52	1.7 s
223	▼ 1	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
224	▼ 1	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	13.8	—	—	—
225	▼ 1	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
226	▼ 1	GPT-4 TurboClosedOpenAI	13.7	$15	28	2.8 s
227	▼ 1	Llama 4 ScoutOpenMeta	13.5	$0.29	132	0.9 s
228	▼ 1	Nova ProClosedAmazon	13.5	$1.4	—	—
229	▼ 2	Command AOpenCohere	13.5	$4.4	38	2.1 s
230	▼ 1	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	284	0.5 s
231	▼ 1	Grok BetaClosedxAI	13.3	—	—	—
232	▼ 1	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
233	▼ 1	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	13.2	$0.37	82	2.3 s
234	▼ 1	GPT-4.1 nanoClosedOpenAI	13.0	$0.18	113	0.7 s
235	▼ 1	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
236	▼ 1	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
237	▼ 1	GPT-4ClosedOpenAI	12.8	$38	—	—
238	▼ 1	Mistral Small 3OpenMistral	12.7	$0.10	137	0.7 s
239	New	MiniCPM-V 4.6 1.3BOpenOpenBMB	12.7	—	—	—
240	▼ 2	Nova LiteClosedAmazon	12.7	$0.11	165	1.0 s
241	▼ 2	GPT-4o miniClosedOpenAI	12.6	$0.26	59	1.2 s
242	▼ 2	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	12.5	—	—	—
243	▼ 2	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	32	1.9 s
244	▼ 2	Granite 4.1 8BOpenIBM	12.4	$0.063	120	0.8 s
245	▼ 2	Sarvam 30B (high)OpenSarvam	12.3	$0.000	262	1.9 s
246	▼ 2	Claude 3 HaikuClosedAnthropic	12.3	$0.50	—	—
247	▼ 2	Mistral SabaClosedMistral	12.1	—	—	—
248	▼ 2	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
249	▼ 2	R1 1776OpenPerplexity	12.0	—	—	—
250	▼ 2	Qwen2.5 TurboClosedAlibaba	12.0	$0.088	64	2.4 s
251	▼ 2	Reka Flash (Sep '24)ClosedReka AI	12.0	$0.35	57	2.5 s
252	▼ 2	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$1.4	57	1.2 s
252	▼ 2	Solar MiniOpenUpstage	11.9	$0.15	—	—
254	▼ 2	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	146	0.9 s
255	▼ 2	Grok-1OpenxAI	11.7	—	—	—
256	▼ 2	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
257	▼ 2	Ministral 3 3BOpenMistral	11.2	$0.10	247	0.5 s
258	▼ 2	Gemini 1.5 Flash-8BClosedGoogle	11.1	—	—	—
259	▼ 2	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	60	1.6 s
260	▼ 2	Granite 4.0 H SmallOpenIBM	10.8	$0.11	232	10 s
261	▼ 2	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
262	▼ 2	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	94	2.0 s
263	▼ 2	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
264	▼ 2	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	59	1.6 s
265	▼ 2	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.020	—	—
266	▼ 2	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	225	0.5 s
267	▼ 2	Phi-4OpenMicrosoft	10.4	$0.22	32	2.1 s
268	▼ 2	Gemma 3 27B InstructOpenGoogle	10.3	$0.14	—	—
269	▼ 2	Claude 3 SonnetClosedAnthropic	10.3	$6.0	—	—
270	▼ 2	Nova MicroClosedAmazon	10.3	$0.061	283	1.0 s
271	▼ 2	Mistral Small (Sep '24)OpenMistral · 1 more variant	10.2	$0.30	138	0.8 s
272	▼ 2	Gemini 1.0 UltraClosedGoogle	10.1	—	—	—
273	▼ 2	Phi-3 Mini Instruct 3.8BOpenMicrosoft	10.1	—	—	—
274	▼ 2	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
275	▼ 2	Phi-4 Multimodal InstructOpenMicrosoft	10.0	$0.000	13	3.8 s
276	▼ 2	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
277	▼ 2	Mistral Large (Feb '24)ClosedMistral	9.9	$6.0	—	—
278	▼ 2	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
279	▼ 2	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
280	▼ 2	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.15	50	1.2 s
281	▼ 2	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
282	▼ 2	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
283	▼ 2	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
284	▼ 2	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
285	▼ 2	Claude 2.1ClosedAnthropic	9.3	—	—	—
286	▼ 2	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
287	▼ 2	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
288	▼ 2	Claude 2.0ClosedAnthropic	9.1	—	—	—
288	▼ 2	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
290	▼ 2	Mistral MediumClosedMistral	9.0	$4.1	76	1.6 s
291	▼ 2	GPT-3.5 TurboClosedOpenAI	9.0	$0.75	—	—
292	▼ 2	Llama 3 Instruct 70BOpenMeta	8.9	$1.2	—	—
293	▼ 2	Arctic InstructOpenSnowflake	8.8	—	—	—
293	▼ 2	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
295	▼ 2	Gemma 3 12B InstructOpenGoogle	8.8	$0.14	—	—
296	▼ 2	LFM 40BClosedLiquid AI	8.8	—	—	—
297	▼ 2	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	45	0.7 s
298	▼ 2	PALM-2ClosedGoogle	8.6	—	—	—
299	▼ 2	Granite 4.1 3BOpenIBM	8.5	—	—	—
300	▼ 2	Gemini 1.0 ProClosedGoogle	8.5	—	—	—
301	▼ 2	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
302	▼ 2	Sarvam M (Reasoning)OpenSarvam	8.4	$0.000	—	—
303	▼ 3	Phi-4 Mini InstructOpenMicrosoft	8.4	$0.000	41	0.8 s
304	▼ 2	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
304	▼ 2	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
306	▼ 2	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
307	▼ 2	Command-R+ (Apr '24)OpenCohere · 1 more variant	8.3	$6.0	—	—
308	▼ 2	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
309	▼ 2	DBRX InstructOpenDatabricks	8.3	—	—	—
310	▼ 2	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	8.3	—	—	—
311	▼ 2	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
312	▼ 2	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
313	▼ 2	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
314	▼ 3	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
315	▼ 2	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
316	▼ 2	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
317	▼ 2	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	8.0	$0.40	124	1.8 s
318	▼ 2	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	182	1.0 s
319	▼ 2	Mixtral 8x7B InstructOpenMistral	7.7	$0.51	—	—
320	▼ 2	Gemma 3 270MOpenGoogle	7.7	—	—	—
321	▼ 2	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
322	▼ 2	Granite 4.0 MicroOpenIBM	7.7	—	—	—
323	▼ 2	Claude InstantClosedAnthropic	7.4	—	—	—
323	▼ 2	Llama 65BOpenMeta	7.4	—	—	—
323	▼ 2	Mistral 7B InstructOpenMistral	7.4	$0.21	115	0.7 s
323	▼ 2	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
327	▼ 2	Granite 4.0 1BOpenIBM	7.3	—	—	—
328	▼ 2	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
329	▼ 2	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	319	24 s
330	▼ 2	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	6.5	$0.40	191	1.7 s
331	▼ 2	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
332	▼ 3	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	39	1.5 s
333	▼ 2	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
334	▼ 2	Gemma 3 4B InstructOpenGoogle	6.3	$0.050	—	—
335	▼ 2	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	89	0.9 s
336	▼ 2	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
337	▼ 2	Granite 4.0 350MOpenIBM	6.1	—	—	—
338	▼ 2	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
339	▼ 2	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	—	—
340	▼ 2	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
341	▼ 2	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
342	▼ 2	Tiny Aya GlobalOpenCohere	4.7	$0.000	—	—

292 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