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	65	116 s
2	—	Claude Opus 4.7 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	57.3	$11	51	21 s
3	—	Gemini 3.1 Pro PreviewClosedGoogle	57.2	$4.5	127	27 s
4	—	GPT-5.4 (xhigh)ClosedOpenAI · 2 more variants	56.8	$5.6	85	185 s
5	New	Qwen3.7 MaxClosedAlibaba	56.6	$3.8	—	—
6	New	Gemini 3.5 Flash (high)ClosedGoogle · 1 more variant	55.3	$3.4	190	23 s
7	▼ 2	Kimi K2.6OpenKimi · 1 more variant	53.9	$1.7	78	2.5 s
8	▼ 2	MiMo-V2.5-ProOpenXiaomi · 1 more variant	53.8	$1.5	57	2.7 s
9	▼ 2	GPT-5.3 Codex (xhigh)ClosedOpenAI	53.6	$4.8	76	114 s
10	▼ 2	Grok 4.3 (high)ClosedxAI · 2 more variants	53.2	$1.6	90	9.2 s
11	▼ 2	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 1 more variant	52.9	$11	45	23 s
12	▼ 2	Muse SparkClosedMeta	52.2	—	—	—
13	▼ 2	Qwen3.6 Max PreviewClosedAlibaba	51.8	$2.9	36	4.7 s
14	▼ 2	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic · 2 more variants	51.7	$6.6	56	111 s
15	▼ 2	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	51.5	$2.2	30	1.9 s
16	▼ 2	GLM-5.1 (Reasoning)OpenZ AI · 1 more variant	51.4	$2.2	56	1.4 s
17	▼ 2	GPT-5.2 (xhigh)ClosedOpenAI · 2 more variants	51.3	$4.8	76	173 s
18	▼ 2	Qwen3.6 PlusClosedAlibaba	50.0	$1.1	53	2.9 s
19	▼ 2	GLM-5 (Reasoning)OpenZ AI · 1 more variant	49.8	$1.6	66	1.6 s
20	▼ 2	Claude Opus 4.5 (Reasoning)ClosedAnthropic · 1 more variant	49.7	$11	51	17 s
21	▼ 2	MiniMax-M2.7OpenMiniMax	49.6	$0.52	50	2.1 s
22	▼ 2	Grok 4.20 0309 v2 (Reasoning)ClosedxAI · 1 more variant	49.3	$3.0	97	25 s
23	▼ 2	MiMo-V2-ProClosedXiaomi	49.2	$1.5	62	2.7 s
24	▼ 2	GPT-5.2 Codex (xhigh)ClosedOpenAI	49.0	$4.8	121	58 s
25	▼ 2	MiMo-V2.5OpenXiaomi	49.0	$0.72	94	3.3 s
26	▼ 2	GPT-5.4 mini (xhigh)ClosedOpenAI · 2 more variants	48.9	$1.7	161	11 s
27	▼ 2	Grok 4.20 0309 (Reasoning)ClosedxAI · 1 more variant	48.5	$3.0	98	22 s
28	▼ 2	Gemini 3 Pro Preview (high)ClosedGoogle · 1 more variant	48.4	$4.5	145	31 s
29	▼ 2	GPT-5.1 (high)ClosedOpenAI · 1 more variant	47.7	$3.4	119	60 s
30	▼ 2	Kimi K2.5 (Reasoning)OpenKimi · 1 more variant	46.8	$1.2	38	3.0 s
31	▼ 2	GLM-5-TurboClosedZ AI	46.8	—	—	—
32	▼ 2	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek · 2 more variants	46.5	$0.18	110	1.2 s
33	▼ 2	Gemini 3 Flash Preview (Reasoning)ClosedGoogle · 1 more variant	46.4	$1.1	164	7.0 s
34	▼ 2	Qwen3.6 27B (Reasoning)OpenAlibaba · 1 more variant	45.8	$1.4	61	3.8 s
35	▼ 2	Qwen3.5 397B A17B (Reasoning)OpenAlibaba · 1 more variant	45.0	$1.4	52	2.6 s
36	▼ 2	MiMo-V2-Omni-0327ClosedXiaomi · 1 more variant	44.9	$0.80	108	2.5 s
37	▼ 2	GPT-5 Codex (high)ClosedOpenAI	44.6	$3.4	189	7.9 s
38	▼ 2	GPT-5 (high)ClosedOpenAI · 4 more variants	44.6	$3.4	79	94 s
39	▼ 2	GPT-5.4 nano (xhigh)ClosedOpenAI · 2 more variants	44.0	$0.46	150	5.5 s
40	▼ 2	Qwen3.6 35B A3B (Reasoning)OpenAlibaba · 1 more variant	43.5	$0.56	191	2.5 s
41	▼ 2	GPT-5.1 Codex (high)ClosedOpenAI	43.1	$3.4	177	5.0 s
42	▼ 2	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	43.0	$6.6	47	12 s
43	▼ 2	GLM 5V Turbo (Reasoning)ClosedZ AI	42.9	—	—	—
44	▼ 2	GLM-4.7 (Reasoning)OpenZ AI · 1 more variant	42.1	$1.0	90	1.3 s
45	▼ 2	Qwen3.5 27B (Reasoning)OpenAlibaba · 1 more variant	42.1	$0.83	86	5.7 s
46	▼ 2	Claude 4.1 Opus (Reasoning)ClosedAnthropic · 1 more variant	42.0	$33	33	13 s
47	▼ 2	MiniMax-M2.5OpenMiniMax	41.9	$0.52	89	1.8 s
48	▼ 2	Hy3-preview (Reasoning)OpenTencent · 1 more variant	41.9	$0.20	104	4.0 s
49	▼ 2	DeepSeek V3.2 (Reasoning)OpenDeepSeek · 1 more variant	41.7	$0.34	—	—
50	▼ 2	Qwen3.5 122B A10B (Reasoning)OpenAlibaba · 1 more variant	41.6	$1.1	132	2.6 s
51	▼ 2	Grok 4ClosedxAI	41.5	$11	—	—
52	▼ 2	MiMo-V2-Flash (Feb 2026)OpenXiaomi · 2 more variants	41.5	$0.15	136	2.2 s
53	▼ 2	GPT-5 mini (high)ClosedOpenAI · 2 more variants	41.2	$0.69	89	101 s
54	▼ 2	Kimi K2 ThinkingOpenKimi	40.9	$1.1	103	2.6 s
55	▼ 2	o3-proClosedOpenAI	40.7	$35	23	121 s
56	▼ 2	Qwen3 Max ThinkingClosedAlibaba · 1 more variant	39.8	$2.4	47	3.6 s
57	▼ 2	MiniMax-M2.1OpenMiniMax	39.4	$0.52	97	1.7 s
58	▼ 2	Mistral Medium 3.5OpenMistral	39.2	$3.0	152	1.7 s
59	▼ 2	Gemma 4 31B (Reasoning)OpenGoogle · 1 more variant	39.2	$0.000	35	1.7 s
60	▼ 2	Claude 4 Opus (Reasoning)ClosedAnthropic · 1 more variant	39.0	$33	31	11 s
61	▼ 2	Claude 4 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	38.7	$6.6	46	14 s
62	▼ 2	Qwen3.5 Omni PlusClosedAlibaba	38.6	$1.5	54	2.4 s
63	▼ 2	GPT-5.1 Codex mini (high)ClosedOpenAI	38.6	$0.69	172	12 s
64	▼ 2	Grok 4.1 Fast (Reasoning)ClosedxAI · 1 more variant	38.6	—	—	—
65	▼ 2	Step 3.5 Flash 2603ClosedStepFun · 1 more variant	38.5	$0.000	206	1.1 s
66	New	Ring-2.6-1TOpenInclusionAI	38.5	—	—	—
67	▼ 3	o3ClosedOpenAI	38.4	$3.5	92	11 s
68	▲ 161	Command A+OpenCohere · 1 more variant	37.2	$0.000	267	0.3 s
69	▼ 4	Qwen3.5 35B A3B (Reasoning)OpenAlibaba · 1 more variant	37.1	$0.69	175	2.3 s
70	▼ 4	Claude 4.5 Haiku (Reasoning)ClosedAnthropic · 1 more variant	37.1	$2.2	92	13 s
71	▼ 4	JT-35B-FlashClosedChina Mobile	36.1	—	—	—
72	▼ 4	MiniMax-M2OpenMiniMax	36.1	$0.52	99	1.8 s
73	▼ 4	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	177	1.2 s
74	▼ 4	Nova 2.0 Pro Preview (medium)ClosedAmazon · 2 more variants	35.7	$3.4	136	13 s
75	▼ 4	Grok 4 Fast (Reasoning)ClosedxAI · 1 more variant	35.1	$0.28	—	—
76	▼ 4	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic · 1 more variant	34.7	—	—	—
77	▼ 4	Gemini 2.5 ProClosedGoogle	34.6	$3.4	128	23 s
78	▼ 4	Nova 2.0 Lite (high)ClosedAmazon · 3 more variants	34.5	$0.85	154	16 s
79	▼ 4	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek · 1 more variant	33.9	$1.9	—	—
80	▼ 4	Ling-2.6-1TOpenInclusionAI	33.6	$0.85	—	—
81	▼ 4	Doubao Seed CodeClosedByteDance Seed	33.5	—	—	—
82	▼ 4	Gemini 3.1 Flash-Lite PreviewClosedGoogle	33.5	$0.56	332	5.3 s
83	▼ 4	gpt-oss-120b (high)OpenOpenAI · 1 more variant	33.3	$0.26	253	0.9 s
84	▼ 4	o4-mini (high)ClosedOpenAI	33.1	$1.9	145	25 s
85	▼ 4	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek · 1 more variant	32.9	$0.31	—	—
86	▼ 4	Mercury 2ClosedInception	32.8	$0.38	840	5.0 s
87	▼ 4	GLM-4.6 (Reasoning)OpenZ AI · 1 more variant	32.5	$0.96	40	3.0 s
88	▼ 4	Qwen3.5 9B (Reasoning)OpenAlibaba · 1 more variant	32.4	$0.11	63	0.7 s
89	▼ 4	K-EXAONE (Reasoning)OpenLG AI Research · 1 more variant	32.1	—	—	—
90	▼ 4	Grok 3 mini Reasoning (high)ClosedxAI	32.1	$0.35	51	0.7 s
91	▼ 4	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	125	1.1 s
92	▼ 4	Qwen3 MaxClosedAlibaba · 1 more variant	31.4	$3.0	33	2.4 s
93	▼ 4	Gemma 4 26B A4B (Reasoning)OpenGoogle · 1 more variant	31.2	$0.20	—	—
94	▼ 4	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle · 3 more variants	31.1	—	—	—
95	▼ 4	Kimi K2 0905OpenKimi · 1 more variant	30.9	$1.1	17	2.9 s
96	▼ 4	o1ClosedOpenAI · 1 more variant	30.7	$26	78	49 s
97	▼ 4	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle · 1 more variant	30.3	—	—	—
98	▼ 4	EXAONE 4.5 33BOpenLG AI Research	30.2	—	—	—
99	▼ 4	GLM-4.7-Flash (Reasoning)OpenZ AI · 1 more variant	30.1	$0.15	83	1.3 s
100	▼ 4	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba · 2 more variants	29.5	$0.84	55	2.9 s
101	▼ 4	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
102	▼ 4	ERNIE 5.0 Thinking PreviewClosedBaidu	29.1	—	—	—
103	▼ 4	Grok Code Fast 1ClosedxAI	28.7	—	—	—
104	▼ 4	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
105	▼ 4	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	93	1.7 s
106	▼ 4	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek · 1 more variant	28.1	$0.83	—	—
107	▼ 4	Nova 2.0 Omni (medium)ClosedAmazon · 2 more variants	28.0	$0.85	—	—
108	▼ 4	Mistral Small 4 (Reasoning)OpenMistral · 1 more variant	27.8	$0.26	135	0.8 s
109	▼ 4	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.2	35	4.2 s
110	▼ 4	Magistral Medium 1.2ClosedMistral	27.1	$2.8	41	1.7 s
111	▼ 4	Qwen3.5 4B (Reasoning)OpenAlibaba · 1 more variant	27.1	$0.060	165	0.5 s
112	▼ 4	DeepSeek R1 0528 (May '25)OpenDeepSeek · 1 more variant	27.1	$2.1	—	—
113	▼ 4	Gemini 2.5 Flash (Reasoning)ClosedGoogle · 1 more variant	27.0	$0.85	200	14 s
114	▼ 4	GPT-5 nano (high)ClosedOpenAI · 2 more variants	26.8	$0.14	147	98 s
115	▼ 4	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	146	2.2 s
116	▼ 4	GLM-4.5 (Reasoning)OpenZ AI	26.4	$1.0	50	3.6 s
117	▼ 4	GPT-4.1ClosedOpenAI	26.3	$3.5	111	0.9 s
118	▼ 4	Ling 2.6 FlashOpenInclusionAI	26.2	$0.15	—	—
119	▼ 4	Solar Pro 3ClosedUpstage	25.9	—	—	—
120	▼ 4	Qwen3.5 Omni FlashClosedAlibaba	25.9	$0.28	260	2.0 s
121	▼ 4	o3-miniClosedOpenAI · 1 more variant	25.9	$1.9	141	7.2 s
122	▼ 4	o1-proClosedOpenAI	25.8	$263	—	—
123	▼ 4	JT-MINIClosedChina Mobile	25.4	—	—	—
124	▼ 4	Grok 3ClosedxAI	25.2	$8.0	—	—
125	▼ 4	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	36	3.5 s
126	▼ 4	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$0.36	61	2.4 s
127	▼ 4	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$0.68	58	3.0 s
128	▼ 4	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	90	2.7 s
129	▼ 4	Sonar Reasoning ProClosedPerplexity	24.6	—	—	—
130	▼ 4	gpt-oss-20B (high)OpenOpenAI · 1 more variant	24.5	$0.088	239	0.8 s
131	▼ 4	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
132	▼ 4	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA · 1 more variant	24.3	$0.096	150	1.4 s
133	▼ 4	LongCat Flash LiteOpenLongCat	23.9	$0.000	114	8.6 s
134	▼ 4	GLM-4.6V (Reasoning)OpenZ AI · 1 more variant	23.4	$0.45	46	4.7 s
135	▼ 4	GLM-4.5-AirOpenZ AI	23.2	$0.37	61	3.1 s
136	▼ 4	Mi:dm K 2.5 ProClosedKorea Telecom	23.1	—	—	—
137	▼ 4	GPT-4.1 miniClosedOpenAI	22.9	$0.70	70	0.8 s
138	▼ 4	Mistral Large 3OpenMistral	22.8	$0.75	48	1.1 s
139	▼ 4	Ring-1TOpenInclusionAI	22.8	—	—	—
140	▼ 4	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba · 2 more variants	22.4	$0.67	139	2.4 s
141	▼ 4	DeepSeek V3 0324OpenDeepSeek · 1 more variant	22.3	$1.2	—	—
142	▼ 4	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
143	▼ 4	Devstral 2OpenMistral	22.0	$0.000	47	1.3 s
144	▼ 4	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
145	▼ 4	Grok 3 Reasoning BetaClosedxAI	21.6	—	—	—
146	▼ 4	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle · 1 more variant	21.6	$0.18	—	—
147	▼ 4	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	21.4	$0.13	301	1.0 s
148	▼ 4	Mistral Medium 3.1ClosedMistral	21.3	$0.80	43	1.8 s
149	▼ 4	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
150	▼ 4	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$0.70	50	2.8 s
151	▼ 4	o1-miniClosedOpenAI	20.4	—	—	—
152	▼ 4	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	146	2.4 s
153	▼ 4	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.35	94	2.7 s
154	▼ 4	GPT-4.5 (Preview)ClosedOpenAI	20.0	—	—	—
155	▼ 4	QwQ 32BOpenAlibaba	19.7	$0.75	29	2.1 s
156	▼ 4	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.34	111	2.4 s
157	▼ 4	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle · 1 more variant	19.6	—	—	—
158	▼ 4	Devstral Small 2OpenMistral	19.5	$0.000	50	1.2 s
159	▼ 4	Motif-2-12.7B-ReasoningClosedMotif Technologies	19.1	—	—	—
160	▼ 4	Ling-1TOpenInclusionAI	19.0	—	—	—
161	▼ 4	Nova PremierClosedAmazon	19.0	$5.0	33	2.9 s
162	▼ 4	Solar Pro 2 (Preview) (Reasoning)ClosedUpstage · 3 more variants	18.8	—	—	—
163	▼ 4	Magistral Medium 1ClosedMistral	18.8	—	—	—
164	▼ 4	Gemma 4 E4B (Reasoning)OpenGoogle · 1 more variant	18.8	—	—	—
165	▼ 4	Mistral Medium 3ClosedMistral	18.8	$0.80	38	1.5 s
166	▼ 4	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA · 1 more variant	18.7	$0.18	50	1.3 s
167	▼ 4	Claude 3.5 HaikuClosedAnthropic	18.7	$1.8	—	—
168	▼ 4	Devstral MediumClosedMistral	18.7	$0.80	82	1.4 s
169	▼ 4	GPT-4o (Aug '24)ClosedOpenAI · 4 more variants	18.6	$4.4	77	1.2 s
170	▼ 4	Gemini 2.0 Flash (Feb '25)ClosedGoogle · 1 more variant	18.5	$0.26	—	—
171	▼ 4	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA · 1 more variant	18.5	—	—	—
172	▼ 4	Llama 4 MaverickOpenMeta	18.4	$0.48	108	1.1 s
173	▼ 4	Qwen3 4B 2507 (Reasoning)OpenAlibaba · 2 more variants	18.2	—	—	—
174	▼ 4	Magistral Small 1.2OpenMistral	18.2	$0.75	105	0.8 s
175	▼ 4	Sarvam 105B (high)OpenSarvam	18.2	$0.000	112	2.2 s
176	▼ 4	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	18.1	—	—	—
177	▼ 4	Devstral Small (May '25)OpenMistral · 1 more variant	18.0	—	—	—
178	▼ 4	Claude 3 OpusClosedAnthropic	18.0	$33	—	—
179	▼ 4	Sonar ReasoningClosedPerplexity	17.9	—	—	—
180	▼ 4	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle · 1 more variant	17.6	$0.18	237	34 s
181	▼ 4	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	53	2.4 s
182	▼ 4	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	78	2.6 s
183	▼ 4	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	—	—	—
184	▼ 4	Magistral Small 1OpenMistral	16.8	—	—	—
185	▼ 4	EXAONE 4.0 32B (Reasoning)OpenLG AI Research · 1 more variant	16.7	—	—	—
186	▼ 4	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	108	2.5 s
187	▼ 4	Qwen3 32B (Reasoning)OpenAlibaba · 1 more variant	16.5	$0.28	86	2.7 s
188	▼ 4	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
189	▼ 4	Qwen3.5 2B (Reasoning)OpenAlibaba · 1 more variant	16.3	$0.040	—	—
190	▼ 4	Qwen2.5 MaxClosedAlibaba	16.3	$2.8	49	3.3 s
191	▼ 4	Qwen3 14B (Reasoning)OpenAlibaba · 1 more variant	16.2	$0.73	58	2.8 s
192	▼ 4	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
193	▼ 4	Qwen3 VL 30B A3B InstructOpenAlibaba	16.0	$0.30	111	2.2 s
194	▼ 4	Gemini 1.5 Pro (Sep '24)ClosedGoogle · 1 more variant	16.0	—	—	—
195	▼ 4	Ministral 3 14BOpenMistral	16.0	$0.20	67	0.7 s
196	▼ 4	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	42	1.7 s
197	▼ 4	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic · 1 more variant	15.9	$6.6	—	—
198	▼ 4	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
199	▼ 4	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
200	▼ 4	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	82	2.4 s
201	▼ 4	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	86	2.1 s
202	▼ 4	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.37	28	3.6 s
203	▼ 4	SonarClosedPerplexity	15.5	—	—	—
204	▼ 4	Step3 VL 10BOpenStepFun	15.5	—	—	—
205	▼ 4	Sonar ProClosedPerplexity	15.2	—	—	—
206	▼ 4	Gemma 4 E2B (Reasoning)OpenGoogle · 1 more variant	15.2	—	—	—
207	▼ 4	QwQ 32B-PreviewOpenAlibaba	15.2	—	—	—
208	▼ 4	GLM-4.5V (Reasoning)OpenZ AI · 1 more variant	15.1	$0.90	38	2.2 s
209	▼ 4	Mistral Large 2 (Nov '24)OpenMistral · 1 more variant	15.1	$3.0	32	2.0 s
210	▼ 4	Mistral Small 3.2OpenMistral	15.1	$0.13	98	0.7 s
211	▼ 4	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	41	2.6 s
212	▼ 4	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.21	105	2.1 s
213	▼ 4	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	23	3.5 s
214	▼ 4	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA · 1 more variant	14.9	$0.30	—	—
215	▼ 4	Ministral 3 8BOpenMistral	14.8	$0.15	85	0.7 s
216	▼ 4	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA · 1 more variant	14.8	$0.070	115	0.6 s
217	▼ 4	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle · 1 more variant	14.7	—	—	—
218	▼ 4	Granite 4.1 30BOpenIBM	14.7	—	—	—
219	▼ 4	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
220	▼ 4	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.62	80	1.7 s
221	▼ 4	Mistral Small 3.1OpenMistral	14.5	$0.14	140	0.7 s
222	▼ 4	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
223	▼ 4	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
224	▼ 4	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	120	2.3 s
225	▼ 4	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	—	—
226	▼ 4	Pixtral LargeOpenMistral	14.0	$3.0	52	1.7 s
227	▼ 4	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
228	▼ 4	Gemini 1.5 Flash (Sep '24)ClosedGoogle · 1 more variant	13.8	—	—	—
229	▼ 4	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
230	▼ 4	GPT-4 TurboClosedOpenAI	13.7	$15	28	2.9 s
231	▼ 4	Llama 4 ScoutOpenMeta	13.5	$0.29	119	0.9 s
232	▼ 4	Nova ProClosedAmazon	13.5	$1.4	—	—
233	▼ 3	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	287	0.5 s
234	▼ 3	Grok BetaClosedxAI	13.3	—	—	—
235	▼ 3	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
236	▼ 3	Qwen3 8B (Reasoning)OpenAlibaba · 1 more variant	13.2	$0.37	39	3.7 s
237	▼ 3	GPT-4.1 nanoClosedOpenAI	13.0	$0.18	139	0.6 s
238	▼ 3	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
239	▼ 3	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
240	▼ 3	GPT-4ClosedOpenAI	12.8	$38	—	—
241	▼ 3	Mistral Small 3OpenMistral	12.7	$0.10	126	0.8 s
242	▼ 3	MiniCPM-V 4.6 1.3BOpenOpenBMB	12.7	—	—	—
243	▼ 3	Nova LiteClosedAmazon	12.7	$0.11	167	1.0 s
244	▼ 3	GPT-4o miniClosedOpenAI	12.6	$0.26	57	1.5 s
245	▼ 3	DeepSeek-V2.5 (Dec '24)OpenDeepSeek · 1 more variant	12.5	—	—	—
246	▼ 3	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	32	1.9 s
247	▼ 3	Granite 4.1 8BOpenIBM	12.4	$0.063	114	0.8 s
248	▼ 3	Sarvam 30B (high)OpenSarvam	12.3	$0.000	262	1.9 s
249	▼ 3	Claude 3 HaikuClosedAnthropic	12.3	$0.50	—	—
250	▼ 3	Mistral SabaClosedMistral	12.1	—	—	—
251	▼ 3	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
252	▼ 3	R1 1776OpenPerplexity	12.0	—	—	—
253	▼ 3	Qwen2.5 TurboClosedAlibaba	12.0	$0.088	65	2.4 s
254	▼ 3	Reka Flash (Sep '24)ClosedReka AI	12.0	$0.35	58	2.5 s
255	▼ 3	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$1.4	58	1.3 s
255	▼ 3	Solar MiniOpenUpstage	11.9	$0.15	—	—
257	▼ 3	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	155	0.8 s
258	▼ 3	Grok-1OpenxAI	11.7	—	—	—
259	▼ 3	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
260	▼ 3	Ministral 3 3BOpenMistral	11.2	$0.10	150	0.5 s
261	▼ 3	Gemini 1.5 Flash-8BClosedGoogle	11.1	—	—	—
262	▼ 3	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	57	1.5 s
263	▼ 3	Granite 4.0 H SmallOpenIBM	10.8	$0.11	388	10 s
264	▼ 3	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
265	▼ 3	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	96	2.0 s
266	▼ 3	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
267	▼ 3	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	58	1.5 s
268	▼ 3	Qwen3.5 0.8B (Reasoning)OpenAlibaba · 1 more variant	10.5	$0.020	—	—
269	▼ 3	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	209	0.6 s
270	▼ 3	Phi-4OpenMicrosoft	10.4	$0.22	18	2.5 s
271	▼ 3	Gemma 3 27B InstructOpenGoogle	10.3	$0.14	—	—
272	▼ 3	Claude 3 SonnetClosedAnthropic	10.3	$6.0	—	—
273	▼ 3	Nova MicroClosedAmazon	10.3	$0.061	281	1.0 s
274	▼ 3	Mistral Small (Sep '24)OpenMistral · 1 more variant	10.2	$0.30	133	0.8 s
275	▼ 3	Gemini 1.0 UltraClosedGoogle	10.1	—	—	—
276	▼ 3	Phi-3 Mini Instruct 3.8BOpenMicrosoft	10.1	—	—	—
277	▼ 3	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
278	▼ 3	Phi-4 Multimodal InstructOpenMicrosoft	10.0	$0.000	16	0.9 s
279	▼ 3	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
280	▼ 3	Mistral Large (Feb '24)ClosedMistral	9.9	$6.0	—	—
281	▼ 3	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
282	▼ 3	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
283	▼ 3	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.15	51	1.2 s
284	▼ 3	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
285	▼ 3	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
286	▼ 3	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
287	▼ 3	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
288	▼ 3	Claude 2.1ClosedAnthropic	9.3	—	—	—
289	▼ 3	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
290	▼ 3	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
291	▼ 3	Claude 2.0ClosedAnthropic	9.1	—	—	—
291	▼ 3	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
293	▼ 3	Mistral MediumClosedMistral	9.0	$4.1	44	2.0 s
294	▼ 3	GPT-3.5 TurboClosedOpenAI	9.0	$0.75	—	—
295	▼ 3	Llama 3 Instruct 70BOpenMeta	8.9	$1.2	—	—
296	▼ 3	Arctic InstructOpenSnowflake	8.8	—	—	—
296	▼ 3	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
298	▼ 3	Gemma 3 12B InstructOpenGoogle	8.8	$0.14	—	—
299	▼ 3	LFM 40BClosedLiquid AI	8.8	—	—	—
300	▼ 3	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	48	0.8 s
301	▼ 3	PALM-2ClosedGoogle	8.6	—	—	—
302	▼ 3	Granite 4.1 3BOpenIBM	8.5	—	—	—
303	▼ 3	Gemini 1.0 ProClosedGoogle	8.5	—	—	—
304	▼ 3	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
305	▼ 3	Sarvam M (Reasoning)OpenSarvam	8.4	$0.000	—	—
306	▼ 3	Phi-4 Mini InstructOpenMicrosoft	8.4	$0.000	—	—
307	▼ 3	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
307	▼ 3	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
309	▼ 3	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
310	▼ 3	Command-R+ (Apr '24)OpenCohere · 1 more variant	8.3	$6.0	—	—
311	▼ 3	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
312	▼ 3	DBRX InstructOpenDatabricks	8.3	—	—	—
313	▼ 3	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research · 1 more variant	8.3	—	—	—
314	▼ 3	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
315	▼ 3	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
316	▼ 3	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
317	▼ 3	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
318	▼ 3	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
319	▼ 3	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
320	▼ 3	Qwen3 1.7B (Reasoning)OpenAlibaba · 1 more variant	8.0	$0.40	126	1.9 s
321	▼ 3	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	182	0.8 s
322	▼ 3	Mixtral 8x7B InstructOpenMistral	7.7	$0.51	—	—
323	▼ 3	Gemma 3 270MOpenGoogle	7.7	—	—	—
324	▼ 3	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
325	▼ 3	Granite 4.0 MicroOpenIBM	7.7	—	—	—
326	▼ 3	Claude InstantClosedAnthropic	7.4	—	—	—
326	▼ 3	Llama 65BOpenMeta	7.4	—	—	—
326	▼ 3	Mistral 7B InstructOpenMistral	7.4	$0.21	84	0.7 s
326	▼ 3	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
330	▼ 3	Granite 4.0 1BOpenIBM	7.3	—	—	—
331	▼ 3	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
332	▼ 3	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	343	27 s
333	▼ 3	Qwen3 0.6B (Reasoning)OpenAlibaba · 1 more variant	6.5	$0.40	195	1.7 s
334	▼ 3	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
335	▼ 3	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	57	1.3 s
336	▼ 3	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
337	▼ 3	Gemma 3 4B InstructOpenGoogle	6.3	$0.050	—	—
338	▼ 3	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	87	0.9 s
339	▼ 3	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
340	▼ 3	Granite 4.0 350MOpenIBM	6.1	—	—	—
341	▼ 3	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
342	▼ 3	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	—	—
343	▼ 3	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
344	▼ 3	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
345	▼ 3	Tiny Aya GlobalOpenCohere	4.7	$0.000	—	—

295 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