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	—	Kimi K2.6OpenKimi	53.9	$1.7	42	2.9 s
8	—	MiMo-V2.5-ProOpenXiaomi	53.8	$1.5	56	3.5 s
9	—	GPT-5.3 Codex (xhigh)ClosedOpenAI	53.6	$4.8	74	96 s
10	—	Grok 4.3ClosedxAI	53.2	$1.6	72	15 s
11	—	Claude Opus 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic	53.0	$11	40	12 s
12	—	Muse SparkClosedMeta	52.2	—	—	—
13	—	Claude Opus 4.7 (Non-reasoning, High Effort)ClosedAnthropic	51.8	$11	37	1.7 s
14	—	Qwen3.6 Max PreviewClosedAlibaba	51.8	$2.9	36	3.5 s
15	—	Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)ClosedAnthropic	51.7	$6.6	51	111 s
16	—	DeepSeek V4 Pro (Reasoning, Max Effort)OpenDeepSeek	51.5	$2.2	34	1.7 s
17	—	GLM-5.1 (Reasoning)OpenZ AI	51.4	$2.2	49	1.9 s
18	—	GPT-5.2 (xhigh)ClosedOpenAI	51.3	$4.8	63	156 s
19	—	GPT-5.5 (low)ClosedOpenAI	50.8	$11	58	2.0 s
20	—	Qwen3.6 PlusClosedAlibaba	50.0	$1.1	53	3.1 s
21	—	DeepSeek V4 Pro (Reasoning, High Effort)OpenDeepSeek	49.8	$2.2	33	1.6 s
22	—	GLM-5 (Reasoning)OpenZ AI	49.8	$1.6	64	1.6 s
23	—	Claude Opus 4.5 (Reasoning)ClosedAnthropic	49.7	$11	45	9.8 s
24	—	MiniMax-M2.7OpenMiniMax	49.6	$0.52	48	2.0 s
25	—	Grok 4.20 0309 v2 (Reasoning)ClosedxAI	49.3	$3.0	87	25 s
26	—	MiMo-V2-ProClosedXiaomi	49.2	$1.5	62	3.2 s
27	—	GPT-5.2 Codex (xhigh)ClosedOpenAI	49.0	$4.8	99	107 s
27	—	MiMo-V2.5OpenXiaomi	49.0	$0.72	93	2.7 s
29	—	GPT-5.4 mini (xhigh)ClosedOpenAI	48.9	$1.7	155	7.9 s
30	—	Grok 4.20 0309 (Reasoning)ClosedxAI	48.5	$3.0	85	28 s
31	—	Gemini 3 Pro Preview (high)ClosedGoogle	48.4	$4.5	126	47 s
32	—	GPT-5.4 (low)ClosedOpenAI	47.9	$5.6	67	2.0 s
33	—	GPT-5.1 (high)ClosedOpenAI	47.7	$3.4	136	25 s
34	—	Kimi K2.5 (Reasoning)OpenKimi	46.8	$1.1	49	3.1 s
35	—	GLM-5-TurboClosedZ AI	46.8	—	—	—
36	—	GPT-5.2 (medium)ClosedOpenAI	46.6	$4.8	—	—
37	—	DeepSeek V4 Flash (Reasoning, Max Effort)OpenDeepSeek	46.5	$0.18	72	1.2 s
38	—	Claude Opus 4.6 (Non-reasoning, High Effort)ClosedAnthropic	46.5	$11	37	1.7 s
39	—	Gemini 3 Flash Preview (Reasoning)ClosedGoogle	46.4	$1.1	162	6.8 s
40	—	Qwen3.6 27B (Reasoning)OpenAlibaba	45.8	$1.4	61	3.6 s
41	—	Qwen3.5 397B A17B (Reasoning)OpenAlibaba	45.1	$1.4	53	2.4 s
42	—	MiMo-V2-Omni-0327ClosedXiaomi	44.9	$0.80	107	2.2 s
43	—	DeepSeek V4 Flash (Reasoning, High Effort)OpenDeepSeek	44.9	$0.18	—	—
44	—	GPT-5 (high)ClosedOpenAI	44.6	$3.4	71	88 s
44	—	GPT-5 Codex (high)ClosedOpenAI	44.6	$3.4	161	9.7 s
46	—	Claude Sonnet 4.6 (Non-reasoning, High Effort)ClosedAnthropic	44.4	$6.6	43	1.4 s
47	—	GPT-5.4 nano (xhigh)ClosedOpenAI	44.0	$0.46	152	4.8 s
48	—	GLM-5.1 (Non-reasoning)OpenZ AI	43.8	$2.2	43	2.5 s
49	—	Qwen3.6 35B A3B (Reasoning)OpenAlibaba	43.5	$0.56	194	2.6 s
50	—	MiMo-V2-OmniClosedXiaomi	43.4	$0.000	110	2.1 s
51	—	GPT-5.1 Codex (high)ClosedOpenAI	43.1	$3.4	167	5.6 s
52	—	Claude Opus 4.5 (Non-reasoning)ClosedAnthropic	43.1	$11	44	1.6 s
53	—	Claude 4.5 Sonnet (Reasoning)ClosedAnthropic	43.0	$6.6	40	9.1 s
54	—	Kimi K2.6 (Non-reasoning)OpenKimi	43.0	$1.7	34	3.0 s
55	—	GLM 5V Turbo (Reasoning)ClosedZ AI	42.9	—	—	—
56	—	Claude Sonnet 4.6 (Non-reasoning, Low Effort)ClosedAnthropic	42.6	$6.6	43	1.2 s
57	—	GLM-4.7 (Reasoning)OpenZ AI	42.1	$1.0	99	1.3 s
58	—	Qwen3.5 27B (Reasoning)OpenAlibaba	42.1	$0.83	88	5.7 s
59	—	GPT-5 (medium)ClosedOpenAI	42.0	$3.4	82	41 s
60	—	Claude 4.1 Opus (Reasoning)ClosedAnthropic	42.0	$33	28	12 s
61	—	MiniMax-M2.5OpenMiniMax	41.9	$0.52	82	1.8 s
62	—	Hy3-preview (Reasoning)OpenTencent	41.9	$0.000	83	3.3 s
63	—	DeepSeek V3.2 (Reasoning)OpenDeepSeek	41.7	$0.34	—	—
64	—	Qwen3.5 122B A10B (Reasoning)OpenAlibaba	41.6	$1.1	151	2.5 s
65	—	Grok 4ClosedxAI	41.5	$8.5	42	20 s
66	—	MiMo-V2-Flash (Feb 2026)OpenXiaomi	41.5	$0.15	134	2.3 s
67	—	Gemini 3 Pro Preview (low)ClosedGoogle	41.3	$4.5	—	—
68	—	GPT-5 mini (high)ClosedOpenAI	41.2	$0.69	72	106 s
69	—	GPT-5.5 (Non-reasoning)ClosedOpenAI	40.9	$11	56	1.0 s
70	—	Kimi K2 ThinkingOpenKimi	40.9	$1.1	120	1.6 s
71	—	o3-proClosedOpenAI	40.7	$35	29	92 s
72	—	GLM-5 (Non-reasoning)OpenZ AI	40.6	$1.6	56	2.2 s
73	—	Qwen3.5 397B A17B (Non-reasoning)OpenAlibaba	40.1	$1.4	54	2.4 s
74	—	Qwen3 Max ThinkingClosedAlibaba	39.9	$2.4	38	3.7 s
75	—	MiniMax-M2.1OpenMiniMax	39.4	$0.52	77	2.0 s
76	—	DeepSeek V4 Pro (Non-reasoning)OpenDeepSeek	39.3	$2.2	33	1.8 s
77	—	MiMo-V2-Flash (Reasoning)OpenXiaomi	39.2	$0.15	129	2.2 s
78	—	Mistral Medium 3.5OpenMistral	39.2	$3.0	145	1.8 s
79	—	GPT-5 (low)ClosedOpenAI	39.2	$3.4	75	8.5 s
80	—	Gemma 4 31B (Reasoning)OpenGoogle	39.2	$0.000	36	1.7 s
81	—	Claude 4 Opus (Reasoning)ClosedAnthropic	39.0	$33	30	7.6 s
82	—	GPT-5 mini (medium)ClosedOpenAI	38.9	$0.69	73	17 s
83	—	Claude 4 Sonnet (Reasoning)ClosedAnthropic	38.7	$6.6	40	10 s
84	—	GPT-5.1 Codex mini (high)ClosedOpenAI	38.6	$0.69	197	3.6 s
84	—	Qwen3.5 Omni PlusClosedAlibaba	38.6	$1.5	54	2.4 s
86	—	Grok 4.1 Fast (Reasoning)ClosedxAI	38.6	$0.28	78	13 s
87	—	Step 3.5 Flash 2603ClosedStepFun	38.5	$0.000	175	1.0 s
88	—	o3ClosedOpenAI	38.4	$3.5	82	8.3 s
89	—	GPT-5.4 nano (medium)ClosedOpenAI	38.1	$0.46	153	3.1 s
90	—	Step 3.5 FlashOpenStepFun	37.8	$0.15	182	1.0 s
91	—	GPT-5.4 mini (medium)ClosedOpenAI	37.7	$1.7	159	11 s
92	—	Kimi K2.5 (Non-reasoning)OpenKimi	37.3	$1.2	45	2.9 s
93	—	Qwen3.5 27B (Non-reasoning)OpenAlibaba	37.2	$0.84	90	5.8 s
94	—	Claude 4.5 Sonnet (Non-reasoning)ClosedAnthropic	37.1	$6.6	38	1.6 s
94	—	Qwen3.6 27B (Non-reasoning)OpenAlibaba	37.1	$1.4	58	3.8 s
96	—	Qwen3.5 35B A3B (Reasoning)OpenAlibaba	37.1	$0.69	167	2.4 s
97	—	Claude 4.5 Haiku (Reasoning)ClosedAnthropic	37.1	$2.2	95	13 s
98	—	DeepSeek V4 Flash (Non-reasoning)OpenDeepSeek	36.5	$0.18	72	1.2 s
99	—	MiniMax-M2OpenMiniMax	36.1	$0.52	70	1.8 s
100	—	Claude 4.1 Opus (Non-reasoning)ClosedAnthropic	36.0	$33	29	2.0 s
101	—	NVIDIA Nemotron 3 Super 120B A12B (Reasoning)OpenNVIDIA	36.0	$0.41	174	1.2 s
102	—	Qwen3.5 122B A10B (Non-reasoning)OpenAlibaba	35.9	$1.1	150	2.4 s
103	—	Nova 2.0 Pro Preview (medium)ClosedAmazon	35.7	$3.4	143	13 s
104	—	MiMo-V2.5-Pro (Non-reasoning)OpenXiaomi	35.6	$1.5	58	3.2 s
105	—	GPT-5.4 (Non-reasoning)ClosedOpenAI	35.4	$5.6	59	0.8 s
106	—	Grok 4 Fast (Reasoning)ClosedxAI	35.1	$0.28	54	9.3 s
107	—	Gemini 3 Flash Preview (Non-reasoning)ClosedGoogle	35.1	$1.1	173	1.1 s
108	—	Claude 3.7 Sonnet (Reasoning)ClosedAnthropic	34.7	—	—	—
109	—	Gemini 2.5 ProClosedGoogle	34.6	$3.4	127	26 s
110	—	Nova 2.0 Lite (high)ClosedAmazon	34.5	$0.85	150	13 s
111	—	GLM-4.7 (Non-reasoning)OpenZ AI	34.2	$1.0	95	1.3 s
112	—	DeepSeek V3.1 Terminus (Reasoning)OpenDeepSeek	33.9	$1.9	—	—
113	—	Hy3-preview (Non-reasoning)OpenTencent	33.7	$0.000	82	3.5 s
114	—	Ling-2.6-1TOpenInclusionAI	33.6	$0.85	—	—
115	—	GPT-5.2 (Non-reasoning)ClosedOpenAI	33.6	$4.8	60	0.9 s
116	—	Doubao Seed CodeClosedByteDance Seed	33.5	—	—	—
116	—	Gemini 3.1 Flash-Lite PreviewClosedGoogle	33.5	$0.56	326	5.7 s
118	—	gpt-oss-120B (high)OpenOpenAI	33.3	$0.26	243	0.9 s
119	—	o4-mini (high)ClosedOpenAI	33.1	$1.9	123	26 s
120	—	Claude 4 Opus (Non-reasoning)ClosedAnthropic	33.0	$33	30	1.9 s
120	—	Claude 4 Sonnet (Non-reasoning)ClosedAnthropic	33.0	$6.6	39	1.3 s
122	—	DeepSeek V3.2 Exp (Reasoning)OpenDeepSeek	32.9	$0.31	—	—
123	—	Mercury 2ClosedInception	32.8	$0.38	685	3.3 s
124	—	GLM-4.6 (Reasoning)OpenZ AI	32.5	$0.96	38	1.4 s
125	—	Qwen3 Max Thinking (Preview)ClosedAlibaba	32.5	$2.4	40	4.1 s
126	—	Qwen3.5 9B (Reasoning)OpenAlibaba	32.4	$0.11	58	0.7 s
127	—	Gemma 4 31B (Non-reasoning)OpenGoogle	32.3	—	—	—
128	—	K-EXAONE (Reasoning)OpenLG AI Research	32.1	—	—	—
129	—	DeepSeek V3.2 (Non-reasoning)OpenDeepSeek	32.1	$0.78	—	—
130	—	Grok 3 mini Reasoning (high)ClosedxAI	32.1	$0.35	169	0.7 s
131	—	Nova 2.0 Pro Preview (low)ClosedAmazon	31.9	$3.4	140	7.4 s
132	—	Trinity Large ThinkingOpenArcee AI	31.9	$0.40	118	0.9 s
133	—	Qwen3.6 35B A3B (Non-reasoning)OpenAlibaba	31.5	$0.84	187	2.4 s
134	—	Qwen3 MaxClosedAlibaba	31.4	$3.0	32	2.8 s
135	—	Gemma 4 26B A4B (Reasoning)OpenGoogle	31.2	$0.20	—	—
136	—	Gemini 2.5 Flash Preview (Sep '25) (Reasoning)ClosedGoogle	31.1	—	—	—
137	—	Claude 4.5 Haiku (Non-reasoning)ClosedAnthropic	31.1	$2.2	86	0.7 s
138	—	Kimi K2 0905OpenKimi	30.9	$1.1	18	2.9 s
139	—	Claude 3.7 Sonnet (Non-reasoning)ClosedAnthropic	30.8	$6.6	—	—
140	—	o1ClosedOpenAI	30.8	$26	93	36 s
141	—	Qwen3.5 35B A3B (Non-reasoning)OpenAlibaba	30.7	$0.69	147	2.4 s
142	—	MiMo-V2-Flash (Non-reasoning)OpenXiaomi	30.4	$0.15	120	2.6 s
143	—	Gemini 2.5 Pro Preview (Mar' 25)ClosedGoogle	30.3	—	—	—
144	—	GLM-4.6 (Non-reasoning)OpenZ AI	30.2	$1.0	39	1.6 s
145	—	EXAONE 4.5 33BOpenLG AI Research	30.2	—	—	—
146	—	GLM-4.7-Flash (Reasoning)OpenZ AI	30.2	$0.15	80	1.1 s
147	—	Nova 2.0 Lite (medium)ClosedAmazon	29.7	$0.85	171	17 s
148	—	Grok 4.20 0309 (Non-reasoning)ClosedxAI	29.7	$3.0	87	0.7 s
149	—	Gemini 2.5 Pro Preview (May' 25)ClosedGoogle	29.5	$3.4	—	—
150	—	Qwen3 235B A22B 2507 (Reasoning)OpenAlibaba	29.5	$0.84	48	2.9 s
151	—	DeepSeek V3.2 SpecialeOpenDeepSeek	29.4	—	—	—
152	—	ERNIE 5.0 Thinking PreviewClosedBaidu	29.1	—	—	—
153	—	Grok 4.20 0309 v2 (Non-reasoning)ClosedxAI	29.0	$3.0	84	0.7 s
154	—	Grok Code Fast 1ClosedxAI	28.7	$0.53	70	6.4 s
155	—	DeepSeek V3.1 Terminus (Non-reasoning)OpenDeepSeek	28.5	$0.45	—	—
156	—	DeepSeek V3.2 Exp (Non-reasoning)OpenDeepSeek	28.4	$0.31	—	—
157	—	Nemotron Cascade 2 30B A3BOpenNVIDIA	28.4	—	—	—
158	—	Qwen3 Coder NextOpenAlibaba	28.3	$0.56	144	1.1 s
159	—	DeepSeek V3.1 (Non-reasoning)OpenDeepSeek	28.1	$0.83	—	—
160	—	Nova 2.0 Omni (medium)ClosedAmazon	28.0	$0.85	—	—
161	—	Mistral Small 4 (Reasoning)OpenMistral	27.8	$0.26	150	0.7 s
162	—	DeepSeek V3.1 (Reasoning)OpenDeepSeek	27.7	$0.87	—	—
163	—	Qwen3 VL 235B A22B (Reasoning)OpenAlibaba	27.6	$2.2	31	3.5 s
164	—	GPT-5.1 (Non-reasoning)ClosedOpenAI	27.4	$3.4	126	1.0 s
165	—	Qwen3.5 9B (Non-reasoning)OpenAlibaba	27.3	—	—	—
166	—	Magistral Medium 1.2ClosedMistral	27.1	$2.8	40	1.6 s
167	—	Gemma 4 26B A4B (Non-reasoning)OpenGoogle	27.1	—	—	—
168	—	Qwen3.5 4B (Reasoning)OpenAlibaba	27.1	$0.060	203	0.5 s
169	—	DeepSeek R1 0528 (May '25)OpenDeepSeek	27.1	$2.1	—	—
170	—	Gemini 2.5 Flash (Reasoning)ClosedGoogle	27.0	$0.85	219	14 s
171	—	GPT-5 nano (high)ClosedOpenAI	26.8	$0.14	127	101 s
172	—	Qwen3 Next 80B A3B (Reasoning)OpenAlibaba	26.7	$1.9	157	2.2 s
173	—	GLM-4.5 (Reasoning)OpenZ AI	26.4	$1.0	43	3.1 s
174	—	Kimi K2OpenKimi	26.3	$1.0	33	1.9 s
175	—	GPT-4.1ClosedOpenAI	26.3	$3.5	105	1.0 s
176	—	Ling 2.6 FlashOpenInclusionAI	26.2	$0.15	206	1.6 s
177	—	Qwen3 Max (Preview)ClosedAlibaba	26.1	$2.4	51	4.2 s
178	—	GPT-5 nano (medium)ClosedOpenAI	25.9	$0.14	142	42 s
179	—	Qwen3.5 Omni FlashClosedAlibaba	25.9	$0.28	241	1.9 s
179	—	Solar Pro 3ClosedUpstage	25.9	—	—	—
181	—	o3-miniClosedOpenAI	25.9	$1.9	129	8.8 s
182	—	o1-proClosedOpenAI	25.8	$263	—	—
183	—	Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)ClosedGoogle	25.7	—	—	—
184	—	JT-MINIClosedChina Mobile	25.4	—	—	—
185	—	o3-mini (high)ClosedOpenAI	25.2	$1.9	133	32 s
186	—	Grok 3ClosedxAI	25.2	$6.0	34	1.8 s
187	—	Seed-OSS-36B-InstructOpenByteDance Seed	25.2	$0.30	37	3.2 s
188	—	Qwen3 235B A22B 2507 InstructOpenAlibaba	25.0	$0.36	56	2.4 s
189	—	Qwen3 Coder 480B A35B InstructOpenAlibaba	24.8	$0.68	55	3.1 s
190	—	Qwen3 VL 32B (Reasoning)OpenAlibaba	24.7	$2.6	87	2.7 s
191	—	Sonar Reasoning ProClosedPerplexity	24.6	—	—	—
192	—	Nova 2.0 Lite (low)ClosedAmazon	24.6	$0.85	156	8.3 s
193	—	gpt-oss-120B (low)OpenOpenAI	24.5	$0.26	250	0.9 s
193	—	gpt-oss-20B (high)OpenOpenAI	24.5	$0.088	262	0.7 s
195	—	MiniMax M1 80kOpenMiniMax	24.4	$0.96	—	—
196	—	GPT-5.4 nano (Non-Reasoning)ClosedOpenAI	24.4	$0.46	146	0.6 s
197	—	Gemini 2.5 Flash Preview (Reasoning)ClosedGoogle	24.3	—	—	—
198	—	NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)OpenNVIDIA	24.3	$0.096	188	1.5 s
199	—	LongCat Flash LiteOpenLongCat	23.9	$0.000	139	8.9 s
200	—	GPT-5 (minimal)ClosedOpenAI	23.9	$3.4	71	1.7 s
201	—	o1-previewClosedOpenAI	23.7	$29	—	—
202	—	Grok 4.1 Fast (Non-reasoning)ClosedxAI	23.6	$0.28	65	0.7 s
203	—	GLM-4.6V (Reasoning)OpenZ AI	23.4	$0.45	39	2.8 s
204	—	K-EXAONE (Non-reasoning)OpenLG AI Research	23.4	—	—	—
205	—	GPT-5.4 mini (Non-Reasoning)ClosedOpenAI	23.3	$1.7	148	0.6 s
206	—	Nova 2.0 Omni (low)ClosedAmazon	23.2	$0.85	—	—
207	—	GLM-4.5-AirOpenZ AI	23.2	$0.37	77	2.9 s
208	—	Grok 4 Fast (Non-reasoning)ClosedxAI	23.1	$0.28	44	0.7 s
209	—	Mi:dm K 2.5 ProClosedKorea Telecom	23.1	—	—	—
209	—	Nova 2.0 Pro Preview (Non-reasoning)ClosedAmazon	23.1	$3.4	107	1.1 s
211	—	GPT-4.1 miniClosedOpenAI	22.9	$0.70	73	0.8 s
212	—	Mistral Large 3OpenMistral	22.8	$0.75	48	1.1 s
213	—	Ring-1TOpenInclusionAI	22.8	—	—	—
214	—	Qwen3.5 4B (Non-reasoning)OpenAlibaba	22.6	$0.060	208	0.5 s
215	—	Qwen3 30B A3B 2507 (Reasoning)OpenAlibaba	22.4	$0.67	140	2.5 s
216	—	DeepSeek V3 0324OpenDeepSeek	22.3	$1.2	—	—
217	—	INTELLECT-3OpenPrime Intellect	22.2	—	—	—
218	—	GLM-4.7-Flash (Non-reasoning)OpenZ AI	22.1	$0.15	103	1.5 s
219	—	Devstral 2OpenMistral	22.0	$0.000	61	1.2 s
220	—	GPT-5 (ChatGPT)ClosedOpenAI	21.8	$3.4	163	0.8 s
221	—	Solar Open 100B (Reasoning)OpenUpstage	21.7	—	—	—
222	—	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)ClosedGoogle	21.7	$0.18	—	—
223	—	Grok 3 Reasoning BetaClosedxAI	21.6	—	—	—
224	New	Nemotron 3 Nano Omni 30B A3B ReasoningOpenNVIDIA	21.4	$0.13	322	0.9 s
225	▼ 1	Mistral Medium 3.1ClosedMistral	21.3	$0.80	88	1.5 s
226	▼ 1	MiniMax M1 40kOpenMiniMax	20.9	—	—	—
227	▼ 1	gpt-oss-20B (low)OpenOpenAI	20.8	$0.095	231	0.7 s
228	▼ 1	Qwen3 VL 235B A22B InstructOpenAlibaba	20.8	$0.70	47	2.9 s
229	▼ 1	GPT-5 mini (minimal)ClosedOpenAI	20.7	$0.69	72	1.3 s
230	▼ 1	Gemini 2.5 Flash (Non-reasoning)ClosedGoogle	20.6	$0.85	191	0.7 s
231	▼ 1	o1-miniClosedOpenAI	20.4	—	—	—
232	▼ 1	Qwen3 Next 80B A3B InstructOpenAlibaba	20.1	$0.88	148	2.3 s
233	▼ 1	Qwen3 Coder 30B A3B InstructOpenAlibaba	20.0	$0.35	106	2.7 s
234	▼ 1	GPT-4.5 (Preview)ClosedOpenAI	20.0	—	—	—
235	▼ 1	Qwen3 235B A22B (Reasoning)OpenAlibaba	19.8	$2.6	53	2.9 s
236	▼ 1	QwQ 32BOpenAlibaba	19.7	$0.75	29	2.1 s
237	▼ 1	Qwen3 VL 30B A3B (Reasoning)OpenAlibaba	19.7	$0.34	110	2.2 s
238	▼ 1	Gemini 2.0 Flash Thinking Experimental (Jan '25)ClosedGoogle	19.6	—	—	—
239	▼ 1	Devstral Small 2OpenMistral	19.5	$0.000	61	1.1 s
240	▼ 1	Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)ClosedGoogle	19.4	$0.18	—	—
241	▼ 1	Motif-2-12.7B-ReasoningClosedMotif Technologies	19.1	—	—	—
242	▼ 1	Ling-1TOpenInclusionAI	19.0	—	—	—
243	▼ 1	Nova PremierClosedAmazon	19.0	$5.0	28	3.1 s
244	▼ 1	DeepSeek R1 (Jan '25)OpenDeepSeek	18.8	$2.4	—	—
245	▼ 1	Solar Pro 2 (Preview) (Reasoning)ClosedUpstage	18.8	—	—	—
246	▼ 1	Magistral Medium 1ClosedMistral	18.8	—	—	—
247	▼ 1	Gemma 4 E4B (Reasoning)OpenGoogle	18.8	$0.54	56	1.7 s
247	▼ 1	Mistral Medium 3ClosedMistral	18.8	$0.80	45	1.5 s
249	▼ 1	Llama Nemotron Super 49B v1.5 (Reasoning)OpenNVIDIA	18.7	$0.18	46	1.6 s
250	▼ 1	Claude 3.5 HaikuClosedAnthropic	18.7	$1.8	—	—
250	▼ 1	Devstral MediumClosedMistral	18.7	$0.80	78	1.4 s
252	▼ 1	GPT-4o (Aug '24)ClosedOpenAI	18.6	$4.4	91	1.4 s
253	▼ 1	Mistral Small 4 (Non-reasoning)OpenMistral	18.6	$0.26	139	0.7 s
254	▼ 1	GPT-4o (March 2025, chatgpt-4o-latest)ClosedOpenAI	18.6	—	—	—
255	▼ 1	Gemini 2.0 Flash (Feb '25)ClosedGoogle	18.5	$0.26	—	—
256	▼ 1	Llama 3.3 Nemotron Super 49B v1 (Reasoning)OpenNVIDIA	18.5	—	—	—
257	▼ 1	Llama 4 MaverickOpenMeta	18.4	$0.48	107	1.0 s
258	▼ 1	Qwen3 4B 2507 (Reasoning)OpenAlibaba	18.2	—	—	—
259	▼ 1	Magistral Small 1.2OpenMistral	18.2	$0.75	106	0.8 s
259	▼ 1	Sarvam 105B (high)OpenSarvam	18.2	$0.000	106	2.3 s
261	▼ 1	Gemini 2.0 Pro Experimental (Feb '25)ClosedGoogle	18.1	—	—	—
262	▼ 1	Devstral Small (May '25)OpenMistral	18.0	—	—	—
262	▼ 1	Nova 2.0 Lite (Non-reasoning)ClosedAmazon	18.0	$0.85	134	1.3 s
264	▼ 1	Claude 3 OpusClosedAnthropic	18.0	$33	—	—
265	▼ 1	Sonar ReasoningClosedPerplexity	17.9	—	—	—
266	▼ 1	Gemini 2.5 Flash Preview (Non-reasoning)ClosedGoogle	17.8	—	—	—
267	▼ 1	Gemini 2.5 Flash-Lite (Reasoning)ClosedGoogle	17.6	$0.18	235	28 s
268	▼ 1	Llama 3.1 Instruct 405BOpenMeta	17.4	$3.7	30	2.4 s
269	▼ 1	GPT-4o (Nov '24)ClosedOpenAI	17.3	$4.4	112	0.9 s
270	▼ 1	Qwen3 VL 32B InstructOpenAlibaba	17.2	$1.2	74	2.8 s
271	▼ 1	DeepSeek R1 Distill Qwen 32BOpenDeepSeek	17.2	—	—	—
272	▼ 1	GLM-4.6V (Non-reasoning)OpenZ AI	17.1	$0.45	40	10 s
273	▼ 1	Qwen3 235B A22B (Non-reasoning)OpenAlibaba	17.0	$0.79	58	2.7 s
274	▼ 1	Magistral Small 1OpenMistral	16.8	—	—	—
275	▼ 1	Gemini 2.0 Flash (experimental)ClosedGoogle	16.8	$0.000	—	—
276	▼ 1	EXAONE 4.0 32B (Reasoning)OpenLG AI Research	16.7	—	—	—
277	▼ 1	Qwen3 VL 8B (Reasoning)OpenAlibaba	16.7	$0.66	110	2.4 s
278	▼ 1	Nova 2.0 Omni (Non-reasoning)ClosedAmazon	16.6	$0.85	201	1.4 s
279	▼ 1	Qwen3 32B (Reasoning)OpenAlibaba	16.5	$0.28	82	2.6 s
280	▼ 1	DeepSeek V3 (Dec '24)OpenDeepSeek	16.5	$0.52	—	—
281	▼ 1	DeepSeek R1 0528 Qwen3 8BOpenDeepSeek	16.4	—	—	—
282	▼ 1	Qwen3.5 2B (Reasoning)OpenAlibaba	16.3	$0.040	—	—
283	▼ 1	Qwen2.5 MaxClosedAlibaba	16.3	$2.8	46	3.3 s
284	▼ 1	Qwen3 14B (Reasoning)OpenAlibaba	16.2	$0.73	59	2.9 s
285	▼ 1	Nanbeige4.1-3BOpenNanbeige	16.1	—	—	—
286	▼ 1	Qwen3 VL 30B A3B InstructOpenAlibaba	16.1	$0.30	108	2.3 s
287	▼ 1	Gemini 1.5 Pro (Sep '24)ClosedGoogle	16.0	—	—	—
287	▼ 1	Solar Pro 2 (Preview) (Non-reasoning)ClosedUpstage	16.0	—	—	—
289	▼ 1	Ministral 3 14BOpenMistral	16.0	$0.20	136	0.7 s
290	▼ 1	DeepSeek R1 Distill Llama 70BOpenDeepSeek	16.0	$0.79	42	1.8 s
291	▼ 1	Claude 3.5 Sonnet (Oct '24)ClosedAnthropic	15.9	$6.6	—	—
292	▼ 1	DeepSeek R1 Distill Qwen 14BOpenDeepSeek	15.8	—	—	—
293	▼ 1	Falcon-H1R-7BOpenTII UAE	15.8	—	—	—
294	▼ 1	Ling-flash-2.0OpenInclusionAI	15.7	$0.25	82	2.7 s
295	▼ 1	Qwen3 Omni 30B A3B (Reasoning)OpenAlibaba	15.6	$0.43	79	1.9 s
296	▼ 1	Qwen2.5 Instruct 72BOpenAlibaba	15.6	$0.37	28	3.6 s
297	▼ 1	SonarClosedPerplexity	15.5	—	—	—
298	▼ 1	Step3 VL 10BOpenStepFun	15.5	—	—	—
299	▼ 1	Qwen3 30B A3B (Reasoning)OpenAlibaba	15.3	$0.18	62	2.5 s
300	▼ 1	Sonar ProClosedPerplexity	15.2	—	—	—
301	▼ 1	Devstral Small (Jul '25)OpenMistral	15.2	$0.15	189	0.7 s
301	▼ 1	Gemma 4 E2B (Reasoning)OpenGoogle	15.2	—	—	—
303	▼ 1	QwQ 32B-PreviewOpenAlibaba	15.2	—	—	—
304	▼ 1	GLM-4.5V (Reasoning)OpenZ AI	15.1	$0.90	41	1.7 s
304	▼ 1	Mistral Large 2 (Nov '24)OpenMistral	15.1	$3.0	30	1.8 s
306	▼ 1	Mistral Small 3.2OpenMistral	15.1	$0.13	138	0.6 s
307	▼ 1	Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)OpenNVIDIA	15.0	$0.90	41	2.6 s
308	▼ 1	Qwen3 30B A3B 2507 InstructOpenAlibaba	15.0	$0.21	116	2.0 s
309	▼ 1	ERNIE 4.5 300B A47BOpenBaidu	15.0	$0.49	22	3.6 s
310	▼ 1	Solar Pro 2 (Reasoning)ClosedUpstage	14.9	—	—	—
311	▼ 1	NVIDIA Nemotron Nano 12B v2 VL (Reasoning)OpenNVIDIA	14.9	$0.30	128	1.1 s
312	▼ 1	Ministral 3 8BOpenMistral	14.8	$0.15	152	0.6 s
313	▼ 1	Gemma 4 E4B (Non-reasoning)OpenGoogle	14.8	$0.54	53	0.9 s
314	▼ 1	NVIDIA Nemotron Nano 9B V2 (Reasoning)OpenNVIDIA	14.8	$0.070	121	1.1 s
315	▼ 1	Gemini 2.0 Flash-Lite (Feb '25)ClosedGoogle	14.7	—	—	—
316	▼ 1	Granite 4.1 30BOpenIBM	14.7	—	—	—
317	▼ 1	NVIDIA Nemotron 3 Nano 4BOpenNVIDIA	14.7	—	—	—
318	▼ 1	Qwen3.5 2B (Non-reasoning)OpenAlibaba	14.7	$0.040	356	0.8 s
319	▼ 1	Llama Nemotron Super 49B v1.5 (Non-reasoning)OpenNVIDIA	14.6	$0.18	46	1.8 s
320	▼ 1	Qwen3 32B (Non-reasoning)OpenAlibaba	14.5	$0.26	86	2.6 s
321	▼ 1	GPT-4o (May '24)ClosedOpenAI	14.5	$7.5	82	1.2 s
322	▼ 1	Llama 3.3 Instruct 70BOpenMeta	14.5	$0.62	77	1.5 s
323	▼ 1	Gemini 2.0 Flash-Lite (Preview)ClosedGoogle	14.5	—	—	—
324	▼ 1	Mistral Small 3.1OpenMistral	14.5	$0.14	135	0.7 s
325	▼ 1	Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)OpenNVIDIA	14.4	—	—	—
326	▼ 1	Kimi Linear 48B A3B InstructOpenKimi	14.4	—	—	—
327	▼ 1	Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)OpenNVIDIA	14.3	—	—	—
328	▼ 1	Qwen3 VL 8B InstructOpenAlibaba	14.3	$0.31	119	2.4 s
329	▼ 1	Qwen3 4B (Reasoning)OpenAlibaba	14.2	$0.40	94	2.4 s
330	▼ 1	Claude 3.5 Sonnet (June '24)ClosedAnthropic	14.2	$6.6	—	—
331	▼ 1	GPT-4o (ChatGPT)ClosedOpenAI	14.1	—	—	—
332	▼ 1	Ring-flash-2.0OpenInclusionAI	14.0	$0.25	88	2.4 s
333	▼ 1	Pixtral LargeOpenMistral	14.0	$3.0	54	1.7 s
334	▼ 1	Grok 2 (Dec '24)OpenxAI	13.9	—	—	—
335	▼ 1	GPT-5 nano (minimal)ClosedOpenAI	13.8	$0.14	121	1.0 s
336	▼ 1	Gemini 1.5 Flash (Sep '24)ClosedGoogle	13.8	—	—	—
337	▼ 1	Qwen3 VL 4B (Reasoning)OpenAlibaba	13.7	—	—	—
338	▼ 1	GPT-4 TurboClosedOpenAI	13.7	$15	30	2.9 s
339	▼ 1	Solar Pro 2 (Non-reasoning)ClosedUpstage	13.6	—	—	—
340	▼ 1	Llama 4 ScoutOpenMeta	13.5	$0.29	142	0.8 s
341	▼ 1	Command AOpenCohere	13.5	$4.4	38	2.4 s
341	▼ 1	Nova ProClosedAmazon	13.5	$1.4	—	—
343	▼ 1	Llama 3.1 Nemotron Instruct 70BOpenNVIDIA	13.4	$1.2	37	1.7 s
344	▼ 1	Grok BetaClosedxAI	13.3	—	—	—
345	▼ 1	Qwen2.5 Instruct 32BOpenAlibaba	13.2	—	—	—
346	▼ 1	Qwen3 8B (Reasoning)OpenAlibaba	13.2	$0.37	81	2.3 s
347	▼ 1	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)OpenNVIDIA	13.2	$0.088	73	0.4 s
348	▼ 1	NVIDIA Nemotron Nano 9B V2 (Non-reasoning)OpenNVIDIA	13.2	$0.086	128	1.1 s
349	▼ 1	GPT-4.1 nanoClosedOpenAI	13.0	$0.18	122	0.7 s
350	▼ 1	Mistral Large 2 (Jul '24)OpenMistral	13.0	$3.0	—	—
351	▼ 1	Qwen3 4B 2507 InstructOpenAlibaba	12.9	—	—	—
352	▼ 1	Qwen2.5 Coder Instruct 32BOpenAlibaba	12.9	—	—	—
353	▼ 1	Qwen3 14B (Non-reasoning)OpenAlibaba	12.8	$0.38	62	2.8 s
354	▼ 1	GPT-4ClosedOpenAI	12.8	$38	—	—
355	▼ 1	GLM-4.5V (Non-reasoning)OpenZ AI	12.7	$0.90	45	25 s
356	▼ 1	Mistral Small 3OpenMistral	12.7	$0.10	133	0.7 s
357	▼ 1	Gemini 2.5 Flash-Lite (Non-reasoning)ClosedGoogle	12.7	$0.18	233	1.1 s
358	▼ 1	Nova LiteClosedAmazon	12.7	$0.11	164	1.0 s
359	▼ 1	GPT-4o miniClosedOpenAI	12.6	$0.26	50	2.7 s
360	▼ 1	Qwen3 30B A3B (Non-reasoning)OpenAlibaba	12.5	$0.13	67	2.3 s
361	▼ 1	DeepSeek-V2.5 (Dec '24)OpenDeepSeek	12.5	—	—	—
362	▼ 1	Qwen3 4B (Non-reasoning)OpenAlibaba	12.5	$0.19	96	2.4 s
363	▼ 1	Llama 3.1 Instruct 70BOpenMeta	12.5	$0.56	33	1.7 s
364	▼ 1	Granite 4.1 8BOpenIBM	12.4	$0.063	92	0.9 s
365	▼ 1	Sarvam 30B (high)OpenSarvam	12.3	$0.000	260	1.9 s
366	▼ 1	Gemini 2.0 Flash Thinking Experimental (Dec '24)ClosedGoogle	12.3	—	—	—
367	▼ 1	DeepSeek-V2.5OpenDeepSeek	12.3	—	—	—
368	▼ 1	Claude 3 HaikuClosedAnthropic	12.3	$0.50	—	—
369	▼ 1	Mistral SabaClosedMistral	12.1	—	—	—
370	▼ 1	DeepSeek R1 Distill Llama 8BOpenDeepSeek	12.1	—	—	—
371	▼ 1	Gemma 4 E2B (Non-reasoning)OpenGoogle	12.1	—	—	—
372	▼ 1	Gemini 1.5 Pro (May '24)ClosedGoogle	12.0	—	—	—
373	▼ 1	R1 1776OpenPerplexity	12.0	—	—	—
374	▼ 1	Qwen2.5 TurboClosedAlibaba	12.0	$0.088	64	2.4 s
375	▼ 1	Reka Flash (Sep '24)ClosedReka AI	12.0	$0.35	58	2.3 s
376	▼ 1	Llama 3.2 Instruct 90B (Vision)OpenMeta	11.9	$1.4	58	1.2 s
376	▼ 1	Solar MiniOpenUpstage	11.9	$0.15	—	—
378	▼ 1	Llama 3.1 Instruct 8BOpenMeta	11.8	$0.10	155	0.9 s
379	▼ 1	Grok-1OpenxAI	11.7	—	—	—
380	▼ 1	Qwen2 Instruct 72BOpenAlibaba	11.7	—	—	—
381	▼ 1	EXAONE 4.0 32B (Non-reasoning)OpenLG AI Research	11.7	—	—	—
382	▼ 1	Ministral 3 3BOpenMistral	11.2	$0.10	278	0.5 s
383	▼ 1	Gemini 1.5 Flash-8BClosedGoogle	11.1	—	—	—
384	▼ 1	Jamba 1.7 LargeOpenAI21 Labs	10.9	$3.5	62	1.7 s
385	▼ 1	Granite 4.0 H SmallOpenIBM	10.8	$0.11	243	10 s
386	▼ 1	Jamba 1.5 LargeOpenAI21 Labs	10.7	$3.5	—	—
387	▼ 1	Qwen3 Omni 30B A3B InstructOpenAlibaba	10.7	$0.43	95	2.0 s
388	▼ 1	Qwen3 8B (Non-reasoning)OpenAlibaba	10.6	$0.19	83	2.4 s
389	▼ 1	DeepSeek-Coder-V2OpenDeepSeek	10.6	—	—	—
390	▼ 1	Jamba 1.6 LargeOpenAI21 Labs	10.6	$3.5	60	1.5 s
391	▼ 1	Qwen3.5 0.8B (Reasoning)OpenAlibaba	10.5	$0.020	—	—
392	▼ 1	LFM2 24B A2BOpenLiquid AI	10.5	$0.053	73	0.6 s
393	▼ 1	Gemini 1.5 Flash (May '24)ClosedGoogle	10.5	—	—	—
394	▼ 1	Phi-4OpenMicrosoft	10.4	$0.22	35	2.1 s
395	▼ 1	Gemma 3 27B InstructOpenGoogle	10.3	$0.14	26	2.0 s
396	▼ 1	Claude 3 SonnetClosedAnthropic	10.3	$6.0	—	—
397	▼ 1	Nova MicroClosedAmazon	10.3	$0.061	279	0.9 s
398	▼ 1	Mistral Small (Sep '24)OpenMistral	10.2	$0.30	130	0.8 s
399	▼ 1	Gemini 1.0 UltraClosedGoogle	10.1	—	—	—
400	▼ 1	Phi-3 Mini Instruct 3.8BOpenMicrosoft	10.1	—	—	—
401	▼ 1	NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)OpenNVIDIA	10.1	$0.30	204	1.1 s
402	▼ 1	Gemma 3n E4B Instruct Preview (May '25)OpenGoogle	10.1	—	—	—
403	▼ 1	Phi-4 Multimodal InstructOpenMicrosoft	10.0	$0.000	17	1.1 s
404	▼ 1	Qwen2.5 Coder Instruct 7BOpenAlibaba	10.0	—	—	—
405	▼ 1	Qwen3.5 0.8B (Non-reasoning)OpenAlibaba	9.9	$0.020	360	0.8 s
406	▼ 1	Mistral Large (Feb '24)ClosedMistral	9.9	$6.0	—	—
407	▼ 1	Mixtral 8x22B InstructOpenMistral	9.8	—	—	—
408	▼ 1	Llama 2 Chat 7BOpenMeta	9.7	$0.10	—	—
409	▼ 1	Llama 3.2 Instruct 3BOpenMeta	9.7	$0.15	51	1.1 s
410	▼ 1	Jamba Reasoning 3BOpenAI21 Labs	9.6	—	—	—
411	▼ 1	Qwen3 VL 4B InstructOpenAlibaba	9.6	—	—	—
412	▼ 1	Qwen1.5 Chat 110BOpenAlibaba	9.5	—	—	—
413	▼ 1	Reka Flash 3OpenReka AI	9.5	$0.35	—	—
414	▼ 1	Claude 2.1ClosedAnthropic	9.3	—	—	—
415	▼ 1	Ling-mini-2.0OpenInclusionAI	9.2	—	—	—
416	▼ 1	DeepSeek R1 Distill Qwen 1.5BOpenDeepSeek	9.1	—	—	—
417	▼ 1	Claude 2.0ClosedAnthropic	9.1	—	—	—
417	▼ 1	DeepSeek-V2-ChatOpenDeepSeek	9.1	—	—	—
419	▼ 1	Mistral Small (Feb '24)ClosedMistral	9.0	$1.5	128	0.8 s
420	▼ 1	Mistral MediumClosedMistral	9.0	$4.1	86	1.5 s
421	▼ 1	GPT-3.5 TurboClosedOpenAI	9.0	$0.75	—	—
422	▼ 1	Llama 3 Instruct 70BOpenMeta	8.9	$1.2	—	—
423	▼ 1	Arctic InstructOpenSnowflake	8.8	—	—	—
423	▼ 1	Qwen Chat 72BOpenAlibaba	8.8	—	—	—
425	▼ 1	Gemma 3 12B InstructOpenGoogle	8.8	$0.14	25	2.4 s
426	▼ 1	LFM 40BClosedLiquid AI	8.8	—	—	—
427	▼ 1	Llama 3.2 Instruct 11B (Vision)OpenMeta	8.7	$0.25	49	0.9 s
428	▼ 1	PALM-2ClosedGoogle	8.6	—	—	—
429	▼ 1	Granite 4.1 3BOpenIBM	8.5	—	—	—
430	▼ 1	Gemini 1.0 ProClosedGoogle	8.5	—	—	—
431	▼ 1	DeepSeek Coder V2 Lite InstructOpenDeepSeek	8.5	—	—	—
432	▼ 1	Phi-4 Mini InstructOpenMicrosoft	8.4	$0.000	44	0.8 s
432	▼ 1	Sarvam M (Reasoning)OpenSarvam	8.4	$0.000	—	—
434	▼ 1	DeepSeek LLM 67B Chat (V1)OpenDeepSeek	8.4	—	—	—
434	▼ 1	Llama 2 Chat 70BOpenMeta	8.4	—	—	—
436	▼ 1	Llama 2 Chat 13BOpenMeta	8.4	—	—	—
437	▼ 1	Command-R+ (Apr '24)OpenCohere	8.3	$6.0	—	—
438	▼ 1	OpenChat 3.5 (1210)OpenOpenChat	8.3	—	—	—
439	▼ 1	DBRX InstructOpenDatabricks	8.3	—	—	—
440	▼ 1	Exaone 4.0 1.2B (Reasoning)OpenLG AI Research	8.3	—	—	—
441	▼ 1	Exaone 4.0 1.2B (Non-reasoning)OpenLG AI Research	8.1	—	—	—
442	▼ 1	LFM2.5-1.2B-ThinkingOpenLiquid AI	8.1	—	—	—
443	▼ 1	Jamba 1.7 MiniOpenAI21 Labs	8.1	—	—	—
444	▼ 1	LFM2 2.6BOpenLiquid AI	8.0	$0.000	—	—
444	▼ 1	LFM2.5-1.2B-InstructOpenLiquid AI	8.0	$0.000	—	—
446	▼ 1	Jamba 1.5 MiniOpenAI21 Labs	8.0	$0.25	—	—
447	▼ 1	Granite 4.0 H 1BOpenIBM	8.0	—	—	—
448	▼ 1	Qwen3 1.7B (Reasoning)OpenAlibaba	8.0	$0.40	127	1.9 s
449	▼ 1	Jamba 1.6 MiniOpenAI21 Labs	7.9	$0.25	183	0.9 s
450	▼ 1	Mixtral 8x7B InstructOpenMistral	7.7	$0.51	—	—
451	▼ 1	Gemma 3 270MOpenGoogle	7.7	—	—	—
452	▼ 1	Apertus 70B InstructOpenSwiss AI Initiative	7.7	$1.3	—	—
453	▼ 1	Granite 4.0 MicroOpenIBM	7.7	—	—	—
454	▼ 1	Claude InstantClosedAnthropic	7.4	—	—	—
454	▼ 1	Command-R (Mar '24)OpenCohere	7.4	$0.75	—	—
454	▼ 1	Llama 65BOpenMeta	7.4	—	—	—
454	▼ 1	Mistral 7B InstructOpenMistral	7.4	$0.21	143	0.6 s
454	▼ 1	Qwen Chat 14BOpenAlibaba	7.4	—	—	—
459	▼ 1	Granite 4.0 1BOpenIBM	7.3	—	—	—
460	▼ 1	LFM2 8B A1BOpenLiquid AI	7.0	$0.000	—	—
461	▼ 1	Granite 3.3 8B (Non-reasoning)OpenIBM	7.0	$0.085	290	27 s
462	▼ 1	Qwen3 1.7B (Non-reasoning)OpenAlibaba	6.8	$0.19	128	1.9 s
463	▼ 1	Qwen3 0.6B (Reasoning)OpenAlibaba	6.5	$0.40	188	1.7 s
464	▼ 1	Gemma 3n E4B InstructOpenGoogle	6.4	$0.025	24	2.2 s
464	▼ 1	Llama 3 Instruct 8BOpenMeta	6.4	$0.070	—	—
466	▼ 1	LFM2 1.2BOpenLiquid AI	6.3	$0.000	—	—
467	▼ 1	Gemma 3 4B InstructOpenGoogle	6.3	$0.050	25	1.8 s
468	▼ 1	Llama 3.2 Instruct 1BOpenMeta	6.3	$0.050	95	0.9 s
469	▼ 1	LFM2.5-VL-1.6BOpenLiquid AI	6.2	$0.000	—	—
470	▼ 1	Granite 4.0 350MOpenIBM	6.1	—	—	—
471	▼ 1	Apertus 8B InstructOpenSwiss AI Initiative	5.9	$0.13	—	—
472	▼ 1	Qwen3 0.6B (Non-reasoning)OpenAlibaba	5.7	$0.19	189	1.7 s
473	▼ 1	Gemma 3 1B InstructOpenGoogle	5.6	$0.000	60	0.8 s
474	▼ 1	Granite 4.0 H 350MOpenIBM	5.4	—	—	—
475	▼ 1	Gemma 3n E2B InstructOpenGoogle	4.8	$0.000	—	—
476	▼ 1	Tiny Aya GlobalOpenCohere	4.7	$0.000	—	—

426 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