Model rankings

Rank	Change	Model	Intelligence	Price $/M	Speed tok/s	First token
1	—	Gemini 3.1 Pro PreviewClosedGoogle	57.2	$4.5	108	30 s
2	—	GPT-5.4 (xhigh)ClosedOpenAI · 1 more variant	57.2	$5.6	73	152 s
3	—	GPT-5.3 Codex (xhigh)ClosedOpenAI	54.0	$4.8	74	96 s
4	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	53.0	$10	41	8.0 s
5	—	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants	51.7	$6.0	45	78 s
6	—	GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants	51.3	$4.8	73	122 s
7	—	GLM-5 (Reasoning)OpenZ AI · 1 more variant	49.8	$1.6	72	1.6 s
8	—	Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant	49.7	$10	46	16 s
9	—	MiniMax-M2.7ClosedMiniMax	49.6	$0.52	45	3.2 s
10	—	MiMo-V2-ProClosedXiaomi	49.2	$1.5	—	—
11	—	GPT-5.2 Codex (xhigh)ClosedOpenAI	49.0	$4.8	116	90 s
12	—	Grok 4.20 Beta 0309 (Reasoning)ClosedxAI · 1 more variant	48.5	$3.0	217	9.8 s
13	—	Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant	48.4	$4.5	108	33 s
14	—	GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants	48.1	$1.7	190	3.4 s
15	—	GPT-5.1 (high)ClosedOpenAI · 1 more variant	47.7	$3.4	111	52 s
16	—	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	46.8	$1.2	43	2.8 s
17	—	GLM-5-TurboClosedZ AI	46.8	—	—	—
18	—	Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant	46.4	$1.1	156	8.0 s
19	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	45.1	$1.4	96	2.3 s
20	—	GPT-5 (high)ClosedOpenAI · 4 more variants	44.6	$3.4	97	70 s
20	—	GPT-5 Codex (high)ClosedOpenAI	44.6	$3.4	170	4.4 s
22	—	GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants	44.4	$0.46	198	3.3 s
23	—	MiMo-V2-OmniClosedXiaomi	43.4	—	—	—
24	—	GPT-5.1 Codex (high)ClosedOpenAI	43.1	$3.4	155	4.6 s
25	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	43.0	$6.0	42	9.8 s
26	—	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	42.1	$1.0	79	1.1 s
27	—	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	42.1	$0.83	87	5.6 s
28	—	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	42.0	$30	29	14 s
29	—	MiniMax-M2.5OpenMiniMax	41.9	$0.52	51	2.1 s
30	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	41.7	$0.32	34	1.9 s
31	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	41.6	$1.1	140	2.3 s
32	—	Grok 4ClosedxAI	41.5	$6.0	52	16 s
33	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	41.5	$0.15	120	2.4 s
34	—	GPT-5 mini (high)ClosedOpenAI · 2 more variants	41.2	$0.69	86	68 s
35	—	Kimi K2 ThinkingOpenKimi	40.9	$1.1	105	1.4 s
36	—	o3-proClosedOpenAI	40.7	$35	26	85 s
37	—	Qwen3 Max ThinkingClosedAlibaba · 1 more variant	39.9	$2.4	37	3.8 s
38	—	MiniMax-M2.1OpenMiniMax	39.4	$0.52	50	2.5 s
39	—	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	39.0	$30	30	9.8 s
40	—	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	38.7	$6.0	42	16 s
41	—	GPT-5.1 Codex mini (high)ClosedOpenAI	38.6	$0.69	163	5.1 s
42	—	Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant	38.6	$0.28	132	8.8 s
43	—	o3ClosedOpenAI	38.4	$3.5	112	4.4 s
44	—	Step 3.5 FlashOpenStepFun	37.8	$0.15	84	3.2 s
45	—	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	37.1	$0.69	165	2.0 s
46	—	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	37.1	$2.0	91	17 s
47	—	MiniMax-M2OpenMiniMax	36.1	$0.52	48	3.0 s
48	▲ 1	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	355	0.7 s
49	▲ 1	Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants	35.7	$3.4	129	13 s
50	▲ 1	Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant	35.1	$0.28	130	4.3 s
51	▲ 1	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	34.7	$6.0	—	—
52	▲ 1	Gemini 2.5 ProClosedGoogle	34.6	$3.4	114	21 s
53	▲ 1	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	33.9	$0.80	—	—
54	▲ 1	Doubao Seed CodeClosedByteDance Seed	33.5	—	—	—
54	▲ 1	Gemini 3.1 Flash-Lite PreviewClosedGoogle	33.5	$0.56	192	7.7 s
56	▲ 1	gpt-oss-120B (high)OpenOpenAI · 1 more variant	33.3	$0.26	260	0.8 s
57	▲ 1	o4-mini (high)ClosedOpenAI	33.1	$1.9	150	23 s
58	▲ 1	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	32.9	$0.32	33	1.9 s
59	▲ 1	Mercury 2ClosedInception	32.8	$0.38	732	3.6 s
60	▲ 1	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	32.5	$0.98	76	1.4 s
61	▲ 1	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	32.4	$0.096	188	1.0 s
62	▲ 1	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	32.1	—	—	—
63	▲ 1	Grok 3 mini Reasoning (high)ClosedxAI	32.1	$0.35	190	0.5 s
64	▲ 1	Qwen3 MaxClosedAlibaba · 1 more variant	31.4	$2.4	62	2.8 s
65	▲ 1	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	31.1	—	—	—
66	▲ 1	Kimi K2 0905OpenKimi · 1 more variant	30.9	$1.2	66	1.0 s
67	▲ 1	o1ClosedOpenAI · 1 more variant	30.8	$26	91	33 s
68	▲ 1	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	30.3	—	—	—
69	▲ 1	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	30.2	$0.15	93	0.9 s
70	▲ 1	Nova 2.0 Lite (medium)ClosedAmazon · 2 more variants	29.7	$0.85	177	11 s
71	▲ 1	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	29.5	$2.6	40	3.0 s
72	▲ 1	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
73	▲ 1	ERNIE 5.0 Thinking PreviewClosedBaidu	29.1	—	—	—
74	▲ 1	Grok Code Fast 1ClosedxAI	28.7	$0.53	172	2.9 s
75	▲ 2	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	151	1.6 s
76	▲ 2	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	28.1	$0.84	—	—
77	▲ 2	Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants	28.0	$0.85	—	—
78	New	Nemotron Cascade 2 30B A3BOpenNVIDIA	27.7	—	—	—
79	▲ 1	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.6	52	3.0 s
80	▲ 6	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	27.2	$0.26	175	0.7 s
81	▲ 1	Magistral Medium 1.2ClosedMistral	27.1	$2.8	96	1.6 s
82	▲ 1	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	27.1	$0.060	252	0.4 s
83	▲ 1	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	27.1	$2.4	—	—
84	▲ 1	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	27.0	$0.85	232	17 s
85	▲ 2	GPT-5 nano (high)ClosedOpenAI · 2 more variants	26.8	$0.14	139	83 s
86	▲ 2	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	149	2.1 s
87	▲ 2	GLM-4.5 (Reasoning)OpenZ AI	26.4	$0.84	50	2.8 s
88	▲ 2	GPT-4.1ClosedOpenAI	26.3	$3.5	105	1.0 s
89	▲ 2	o3-miniClosedOpenAI · 1 more variant	25.9	$1.9	151	8.2 s
90	▲ 2	o1-proClosedOpenAI	25.8	$263	—	—
91	▲ 2	Grok 3ClosedxAI	25.2	$6.0	75	1.3 s
92	▲ 2	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	37	3.1 s
93	▲ 2	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$1.2	53	2.4 s
94	▲ 2	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$3.0	62	3.0 s
95	▲ 2	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	91	2.7 s
96	▲ 2	Sonar Reasoning ProClosedPerplexity	24.6	—	—	—
97	▲ 2	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.095	312	0.7 s
98	▲ 2	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
99	▲ 2	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.11	162	1.9 s
100	▲ 3	LongCat Flash LiteOpenLongCat	23.9	$0.000	107	6.1 s
101	▲ 4	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	23.4	$0.45	26	2.0 s
102	▲ 4	GLM-4.5-AirOpenZ AI	23.2	$0.43	103	1.2 s
103	▲ 4	Mi:dm K 2.5 ProClosedKorea Telecom	23.1	—	—	—
104	▲ 4	GPT-4.1 miniClosedOpenAI	22.9	$0.70	79	0.8 s
105	▲ 4	Mistral Large 3OpenMistral	22.8	$0.75	47	1.1 s
106	▲ 4	Ring-1TOpenInclusionAI	22.8	—	—	—
107	▲ 4	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.4	$0.75	166	2.3 s
108	▲ 4	DeepSeek V3 0324OpenDeepSeek · 1 more variant	22.3	$1.3	—	—
109	▲ 4	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
110	▲ 4	Devstral 2OpenMistral	22.0	$0.000	77	0.8 s
111	▲ 4	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
112	▲ 4	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	21.7	$0.18	354	5.5 s
113	▲ 4	Grok 3 Reasoning BetaClosedxAI	21.6	—	—	—
114	▲ 4	Mistral Medium 3.1ClosedMistral	21.3	$0.80	63	1.5 s
115	▲ 4	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
116	▲ 4	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$1.2	57	2.6 s
117	▲ 5	o1-miniClosedOpenAI	20.4	—	—	—
118	▲ 5	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	152	2.2 s
119	▲ 6	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.90	26	2.7 s
120	▲ 6	GPT-4.5 (Preview)ClosedOpenAI	20.0	—	—	—
121	▲ 6	QwQ 32BOpenAlibaba	19.7	$0.75	—	—
122	▲ 6	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.75	112	2.1 s
123	▲ 6	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	19.6	—	—	—
124	▲ 6	Devstral Small 2OpenMistral	19.5	$0.000	177	0.6 s
125	▲ 6	Motif-2-12.7B-ReasoningClosedMotif Technologies	19.1	—	—	—
126	▲ 6	Ling-1TOpenInclusionAI	19.0	—	—	—
127	▲ 6	Nova PremierClosedAmazon	19.0	$5.0	30	2.8 s
128	▲ 6	Solar Pro 2 (Preview) (Reasoning)ClosedUpstage · 3 more variants	18.8	—	—	—
129	▲ 6	Magistral Medium 1ClosedMistral	18.8	—	—	—
130	▲ 6	Mistral Medium 3ClosedMistral	18.8	$0.80	59	1.2 s
131	▲ 6	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	50	1.2 s
132	▲ 6	Claude 3.5 HaikuClosedAnthropic	18.7	$1.6	—	—
132	▲ 6	Devstral MediumClosedMistral	18.7	$0.80	143	1.2 s
134	▲ 6	GPT-4o (Aug '24)ClosedOpenAI · 4 more variants	18.6	$4.4	114	1.0 s
135	▲ 8	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	18.5	$0.26	—	—
136	▲ 8	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
137	▲ 8	Llama 4 MaverickOpenMeta	18.4	$0.46	119	0.9 s
138	▲ 8	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	18.2	—	—	—
139	▲ 8	Magistral Small 1.2OpenMistral	18.2	$0.75	167	0.8 s
139	▲ 8	Sarvam 105B (high)OpenSarvam	18.2	$0.000	125	2.4 s
141	▲ 8	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	18.1	—	—	—
142	▲ 8	Devstral Small (May '25)OpenMistral · 1 more variant	18.0	$0.075	—	—
143	▲ 8	Claude 3 OpusClosedAnthropic	18.0	$30	—	—
144	▲ 8	Sonar ReasoningClosedPerplexity	17.9	—	—	—
145	▲ 8	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	17.6	$0.18	285	22 s
146	▲ 8	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	29	2.2 s
147	▲ 8	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	72	2.7 s
148	▲ 8	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	$0.27	60	0.8 s
149	▲ 8	Magistral Small 1OpenMistral	16.8	—	—	—
150	▲ 8	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	16.7	—	—	—
151	▲ 8	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	116	2.4 s
152	▲ 8	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	16.5	$2.6	97	2.4 s
153	▲ 8	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
154	▲ 8	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	16.3	$0.040	346	0.4 s
155	▲ 8	Qwen2.5 MaxClosedAlibaba	16.3	$2.8	47	3.1 s
156	▲ 8	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	16.2	$1.3	63	2.7 s
157	▲ 8	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
158	▲ 8	Qwen3 VL 30B A3B InstructOpenAlibaba	16.1	$0.35	111	2.2 s
159	▲ 8	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	16.0	—	—	—
160	▲ 9	Ministral 3 14BOpenMistral	16.0	$0.20	108	0.6 s
161	▲ 9	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	49	1.6 s
162	▲ 9	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	15.9	$6.0	—	—
163	▲ 9	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
164	▲ 9	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
165	▲ 9	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	65	2.5 s
166	▲ 9	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	94	1.9 s
167	▲ 9	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.000	27	3.4 s
168	▲ 9	SonarClosedPerplexity	15.5	—	—	—
169	▲ 9	Step3 VL 10BOpenStepFun	15.5	—	—	—
170	▲ 9	Sonar ProClosedPerplexity	15.2	—	—	—
171	▲ 9	QwQ 32B-PreviewOpenAlibaba	15.2	$0.14	60	0.9 s
172	▲ 9	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	15.1	$0.90	55	1.9 s
172	▲ 9	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	15.1	$3.0	36	1.5 s
174	▲ 9	Mistral Small 3.2OpenMistral	15.1	$0.15	191	0.5 s
175	▲ 9	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	41	2.5 s
176	▲ 9	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.35	52	2.0 s
177	▲ 9	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	33	5.8 s
178	▲ 9	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	130	0.6 s
179	▲ 9	Ministral 3 8BOpenMistral	14.8	$0.15	186	0.5 s
180	▲ 9	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	123	0.6 s
181	▲ 9	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	14.7	—	—	—
182	▲ 9	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
183	▲ 9	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.61	95	1.3 s
184	▲ 9	Mistral Small 3.1OpenMistral	14.5	$0.15	136	0.7 s
185	▲ 9	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
186	▲ 9	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
187	▲ 9	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	119	2.2 s
188	▲ 10	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	85	2.1 s
189	▲ 10	Pixtral LargeOpenMistral	14.0	$3.0	56	1.4 s
190	▲ 11	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
191	▲ 11	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	13.8	—	—	—
192	▲ 11	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
193	▲ 11	GPT-4 TurboClosedOpenAI	13.7	$15	30	2.9 s
194	▲ 11	Llama 4 ScoutOpenMeta	13.5	$0.29	128	0.7 s
195	▲ 11	Command AOpenCohere	13.5	$4.4	37	3.3 s
195	▲ 11	Nova ProClosedAmazon	13.5	$1.4	—	—
197	▲ 11	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	36	1.7 s
198	▲ 11	Grok BetaClosedxAI	13.3	—	—	—
199	▲ 11	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
200	▲ 11	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	13.2	$0.66	81	2.2 s
201	▲ 11	GPT-4.1 nanoClosedOpenAI	13.0	$0.18	173	0.6 s
202	▲ 11	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
203	▲ 11	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
204	New	GPT-4ClosedOpenAI	12.8	$38	—	—
205	▲ 10	Mistral Small 3OpenMistral	12.7	$0.15	133	0.6 s
206	▲ 10	Nova LiteClosedAmazon	12.7	$0.11	174	0.7 s
207	▲ 10	GPT-4o miniClosedOpenAI	12.6	$0.26	42	2.8 s
208	▲ 10	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	12.5	—	—	—
209	▲ 10	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	27	1.7 s
210	▲ 10	Sarvam 30B (high)OpenSarvam	12.3	$0.000	153	1.9 s
211	▲ 10	Claude 3 HaikuClosedAnthropic	12.3	$0.50	139	1.1 s
212	▲ 11	Mistral SabaClosedMistral	12.1	—	—	—
213	▲ 11	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
214	▲ 12	R1 1776OpenPerplexity	12.0	—	—	—
215	▲ 12	Qwen2.5 TurboClosedAlibaba	12.0	$0.088	64	2.3 s
216	▲ 12	Reka Flash (Sep '24)ClosedReka AI	12.0	$0.35	58	1.9 s
217	▲ 12	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$0.72	56	0.9 s
217	New	Solar MiniOpenUpstage	11.9	$0.15	—	—
219	▲ 11	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	156	0.9 s
220	New	Grok-1OpenxAI	11.7	—	—	—
221	▲ 10	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
222	▲ 10	Ministral 3 3BOpenMistral	11.2	$0.10	275	0.4 s
223	▲ 10	Gemini 1.5 Flash-8BClosedGoogle	11.1	—	—	—
224	▲ 11	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	59	1.3 s
225	▲ 11	Granite 4.0 H SmallOpenIBM	10.8	$0.11	452	10 s
226	▲ 11	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
227	▲ 11	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	95	1.9 s
228	▲ 12	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
229	▲ 12	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	62	1.4 s
230	▲ 12	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.020	413	0.4 s
231	▲ 12	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	80	0.4 s
232	▲ 12	Phi-4OpenMicrosoft Azure	10.4	$0.22	35	2.0 s
233	▲ 12	Gemma 3 27B InstructOpenGoogle	10.3	$0.000	31	2.0 s
234	▲ 12	Claude 3 SonnetClosedAnthropic	10.3	$6.0	—	—
235	▲ 12	Nova MicroClosedAmazon	10.3	$0.061	313	0.7 s
236	▲ 12	Mistral Small (Sep '24)OpenMistral · 1 more variant	10.2	$0.30	145	0.6 s
237	▲ 12	Gemini 1.0 UltraClosedGoogle	10.1	—	—	—
238	New	Phi-3 Mini Instruct 3.8BOpenMicrosoft Azure	10.1	—	—	—
239	▲ 11	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
240	▲ 11	Phi-4 Multimodal InstructOpenMicrosoft Azure	10.0	$0.000	17	1.2 s
241	▲ 11	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
242	▲ 11	Mistral Large (Feb '24)ClosedMistral	9.9	$6.0	—	—
243	▲ 11	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
244	New	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
245	▲ 10	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.085	51	0.8 s
246	▲ 10	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
247	▲ 10	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
248	▲ 10	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
249	▲ 10	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
250	▲ 11	Claude 2.1ClosedAnthropic	9.3	—	—	—
251	▲ 11	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
252	▲ 11	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
253	▲ 11	Claude 2.0ClosedAnthropic	9.1	—	—	—
253	▲ 11	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
255	▲ 11	Mistral MediumClosedMistral	9.0	$4.1	56	1.5 s
256	New	GPT-3.5 TurboClosedOpenAI	9.0	$0.75	—	—
257	New	Llama 3 Instruct 70BOpenMeta	8.9	$0.87	—	—
258	New	Arctic InstructOpenSnowflake	8.8	—	—	—
258	▲ 9	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
260	▲ 8	Gemma 3 12B InstructOpenGoogle	8.8	$0.000	30	37 s
261	▲ 8	LFM 40BClosedLiquid AI	8.8	—	—	—
262	▲ 8	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.16	49	0.6 s
263	New	PALM-2ClosedGoogle	8.6	—	—	—
264	▲ 7	Gemini 1.0 ProClosedGoogle	8.5	—	—	—
265	▲ 7	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
266	▲ 7	Phi-4 Mini InstructOpenMicrosoft Azure	8.4	$0.000	43	0.8 s
266	▲ 7	Sarvam M (Reasoning)OpenSarvam	8.4	—	—	—
268	New	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
268	New	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
270	New	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
271	▲ 4	Command-R+ (Apr '24)OpenCohere · 1 more variant	8.3	$6.0	—	—
272	New	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
273	▲ 3	DBRX InstructOpenDatabricks	8.3	—	—	—
274	▲ 3	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	8.3	—	—	—
275	▲ 4	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
276	▲ 4	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
277	▲ 4	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
277	▲ 4	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
279	▲ 4	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
280	▲ 4	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
281	▲ 4	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	8.0	$0.40	127	1.7 s
282	▲ 4	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	188	0.8 s
283	▲ 4	Mixtral 8x7B InstructOpenMistral	7.7	$0.56	—	—
284	▲ 4	Gemma 3 270MOpenGoogle	7.7	—	—	—
285	▲ 4	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	62	2.7 s
286	▲ 4	Granite 4.0 MicroOpenIBM	7.7	—	—	—
287	▲ 5	Claude InstantClosedAnthropic	7.4	—	—	—
287	New	Llama 65BOpenMeta	7.4	—	—	—
287	New	Mistral 7B InstructOpenMistral	7.4	$0.25	185	0.5 s
287	New	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
291	▲ 2	Granite 4.0 1BOpenIBM	7.3	—	—	—
292	▲ 3	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
293	▲ 3	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	—	—
294	▲ 3	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	6.5	$0.40	180	1.6 s
295	▲ 3	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	24	1.1 s
295	New	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
297	▲ 2	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
298	▲ 2	Gemma 3 4B InstructOpenGoogle	6.3	$0.000	33	1.5 s
299	▲ 2	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	97	0.9 s
300	▲ 2	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
301	▲ 2	Granite 4.0 350MOpenIBM	6.1	—	—	—
302	▲ 2	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	136	2.3 s
303	▲ 2	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	44	0.8 s
304	▲ 2	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
305	▲ 2	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
306	New	Tiny Aya GlobalOpenCohere	4.7	—	—	—

256 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