Leaderboard | Text

Models

Choose model family

Claude by Anthropic

Mistral by Mistral AI

Choose topic

All topics Facts and Information Creative Writing and Ideation Logic and Problem-Solving Task Completion Coding

Language

Choose language

All languages English Chinese Arabic Spanish Indonesian Japanese

More filters

Show inactive models

Hide models that are no longer actively available on Yupp.

Turns

Filter model performance by the number of turns in a conversation.

All Single turn Multiple turns

Open license models

Filter the leaderboard to only show models that have an open license.

All selected Open license Proprietary license

1388

Claude Opus 4.6 (Thinking)

1367

GPT-5.4 (High)

1339

GPT-5.4

1328

Claude Opus 4.6

1326

Nova Experimental Chat 10-20

1325

Claude Sonnet 4.6 (Thinking)

1307

GPT-5.1 (Medium)

1268

Gemini 3.1 Pro

1266

GPT-5.2 Instant

1258

GPT-5.1 (High)

1249

gpt-oss-120b

1243

GPT-5 (High)

1236

Mistral Medium 3.1

1233

GPT-5.1

1232

Claude Sonnet 4.6

Last updated about 1 month ago

Rank	Overall	Name	VIBE Score	Confidence Interval	Votes	Downvote %	Abort %	Speed	Latency	Context	Cost (Input)	Cost (Output)
1	1	Claude Opus 4.6 (Thinking)	1388	±10	1.8K	0.8%	2.5%	56 tps	1.6s	200K	$5.00	$25.00
2	4	GPT-5.4 (High)	1367	±15	825	1.2%	4.6%	68 tps	7.9s	1M	$2.50	$15.00
3	2	GPT-5.4	1339	±15	530	0.9%	2.6%	55 tps	0.8s	1M	$2.50	$15.00
4	2	Claude Opus 4.6	1328	±8	2.3K	0.9%	2.1%	48 tps	1.7s	200K	$5.00	$25.00
5	37	Nova Experimental Chat 10-20	1326	±6	2.1K	3.3%	<0.1%	30 tps	0.5s	98K	$0	$0
6	5	Claude Sonnet 4.6 (Thinking)	1325	±7	1.6K	1.2%	4.7%	57 tps	1.1s	200K	$3.00	$15.00
7	8	GPT-5.1 (Medium)	1307	±7	1.2K	2.5%	<0.1%	86 tps	3.8s	400K	$0.83	$6.67
8	6	Gemini 3.1 Pro	1268	±8	4.3K	0.7%	3.5%	35 tps	4.1s	1M	$2.00	$12.00
9	10	GPT-5.2 Instant	1266	±4	6.2K	0.7%	1.7%	52 tps	2.0s	400K	$1.75	$14.00
10	8	GPT-5.1 (High)	1258	±6	5.3K	1.3%	3.2%	76 tps	6.9s	400K	$1.25	$10.00
11	48	gpt-oss-120b	1249	±4	7.3K	1.3%	0.7%	213 tps	0.5s	131K	$0.11	$0.50
12	26	GPT-5 (High)	1243	±7	3K	2.3%	4.5%	81 tps	35.9s	400K	$1.25	$10.00
13	19	Mistral Medium 3.1	1236	±5	5.1K	2.3%	<0.1%	77 tps	0.7s	128K	$0.40	$2.00
14	8	GPT-5.1	1233	±8	3.3K	1.4%	2.3%	71 tps	1.4s	400K	$1.42	$11.33
15	4	Claude Sonnet 4.6	1232	±11	1.6K	0.9%	1.6%	47 tps	1.2s	200K	$3.00	$15.00
16	33	Qwen3 30B A3B Instruct 2507	1226	±8	5.6K	2.2%	1.2%	55 tps	1.3s	131K	$0.13	$0.72
17	10	Gemini 3 Pro	1217	±5	11.7K	0.9%	2.1%	50 tps	3.6s	1M	$2.00	$12.00
18	104	Grok 3 Beta	1209	±16	535	<0.1%	<0.1%	58 tps	0.8s	131K	$3.00	$15.00
19	22	GPT-5 Chat	1208	±5	10.4K	2.2%	1.3%	95 tps	0.9s	400K	$1.25	$10.00
20	29	Qwen3 VL 235B A22B Instruct	1202	±10	1.8K	4.5%	3.1%	75 tps	1.9s	129K	$0.37	$1.81
21	33	Qwen Plus 0728	1199	±11	850	2.3%	<0.1%	55 tps	0.9s	1M	$0.40	$1.20
22	33	Qwen3 Next 80B A3B Instruct	1198	±7	3.4K	3.0%	0.6%	84 tps	1.1s	256K	$0.20	$1.42
23	48	OpenAI o1-mini	1195	±4	10.8K	1.1%	<0.1%	118 tps	N/A	128K	$1.13	$4.51
24	13	GPT-5.3 Instant	1191	±11	1.6K	1.2%	0.9%	63 tps	0.8s	400K	$1.75	$14.00
25	17	Grok 4.20 Beta Reasoning	1190	±17	540	0.9%	1.1%	77 tps	4.5s	2M	$2.00	$5.50
26	14	Gemini 3 Pro (Low)	1189	±6	4.8K	0.9%	2.4%	51 tps	3.5s	1M	$2.00	$12.00
27	32	Gemini 2.5 Pro High	1182	±3	6.7K	2.2%	1.5%	48 tps	2.3s	1M	$1.25	$10.00
28	40	Qwen3 235B A22B Instruct 2507	1178	±6	5.1K	1.9%	6.8%	13 tps	1.9s	262K	$0.13	$0.52
29	106	Claude Sonnet 3.5 v2	1177	±8	1.6K	1.2%	<0.1%	46 tps	1.4s	200K	$3.00	$15.00
30	17	GPT-5.2 (High)	1177	±7	7.4K	0.8%	6.7%	18 tps	16.3s	400K	$1.75	$14.00
31	111	Claude Sonnet 3.7	1173	±6	2.8K	1.9%	<0.1%	39 tps	1.6s	200K	$3.00	$15.00
32	14	Gemini 3 Flash Preview Thinking	1173	±5	4.4K	0.6%	1.6%	3 tps	6.2s	1M	$0.50	$3.00
33	16	Nova Experimental Chat 11-10	1171	±6	2.7K	1.3%	0.4%	84 tps	8.9s	98K	$0	$0
34	81	GPT-4o	1170	±9	2.3K	2.8%	1.0%	49 tps	2.4s	128K	$3.71	$12.57
35	16	GPT-5.2	1168	±6	3K	1.2%	4.1%	18 tps	2.7s	400K	$1.75	$14.00
36	17	Gemini 3 Flash Preview	1166	±7	2.4K	0.6%	1.3%	138 tps	1.4s	1M	$0.50	$3.00
37	60	Gemini 2.5 Flash Preview 0925	1163	±7	2.7K	2.9%	1.2%	5 tps	0.9s	1M	$0.13	$0.97
38	43	Gemini 2.5 Flash Thinking Preview 0925	1159	±5	3.1K	2.7%	<0.1%	111 tps	4.7s	1M	$0.30	$2.50
39	56	Gemini 2.5 Pro Low	1159	±6	3.3K	3.5%	<0.1%	89 tps	2.4s	1M	$1.25	$10.00
40	100	Gemini 2.5 Flash Preview	1159	±11	1K	1.4%	<0.1%	138 tps	6.9s	1M	$0.15	$0.60
41	7	Claude Opus 4.5 (Thinking)	1155	±5	5.3K	1.6%	1.8%	49 tps	1.4s	200K	$5.00	$25.00
42	26	Grok 4.1 Fast Non-Reasoning	1151	±6	3.2K	1.8%	0.9%	101 tps	0.5s	2M	$0.20	$0.50
43	68	Qwen Plus (Aug'24)	1150	±5	7.5K	1.4%	1.4%	53 tps	1.3s	30K	$0.40	$1.20
44	101	gpt-oss-20b	1150	±7	4K	1.7%	0.5%	216 tps	0.5s	131K	$0.06	$0.26
45	147	Arcee AI Maestro Reasoning	1149	±7	2K	1.4%	<0.1%	85 tps	0.3s	131K	$0.90	$3.30
46	52	Qwen3.5 122B A17B	1147	±13	765	1.9%	1.5%	82 tps	1.4s	256K	$0.40	$3.20
47	17	Claude Opus 4.5	1144	±8	2.4K	2.1%	1.5%	45 tps	1.5s	200K	$5.00	$25.00
48	100	Qwen Plus 0728 (Thinking)	1141	±14	500	2.0%	<0.1%	56 tps	1.1s	1M	$0.40	$4.00
49	37	Kimi K2.5 Instant	1140	±10	1.1K	1.4%	2.9%	32 tps	3.0s	262K	$0.50	$3.00
50	48	Step 3.5 Flash	1140	±15	965	0.5%	2.2%	109 tps	0.6s	256K	$0.05	$0.15
51	37	Qwen3 Omni 30B A3B Thinking	1139	±7	1.6K	1.2%	3.7%	67 tps	1.2s	66K	$0.97	$1.79
52	29	Nova Experimental Chat 12-10	1138	±9	1.9K	0.5%	2.4%	84 tps	12.9s	98K	$0	$0
53	111	Solar Pro 3 (Reasoning)	1136	±13	830	1.2%	3.2%	118 tps	1.2s	131K	$0.15	$0.60
54	10	Claude Sonnet 4.5 (Thinking)	1136	±5	6.8K	2.7%	1.9%	44 tps	1.1s	200K	$3.00	$15.00
55	42	GPT-5.2 (Extra High)	1131	±5	3.7K	0.9%	13.2%	17 tps	20.5s	400K	$1.75	$14.00
56	26	Claude Haiku 4.5 (Extended Thinking)	1129	±5	3.6K	1.6%	1.4%	115 tps	0.7s	200K	$1.00	$5.00
57	213	DeepSeek R1T Chimera	1128	±8	1.9K	2.5%	<0.1%	46 tps	1.1s	164K	$0.09	$0.36
58	42	Qwen3 Max Instruct Preview	1126	±4	4.3K	2.8%	1.1%	31 tps	1.7s	256K	$1.43	$6.61
59	44	Gemini 2.5 Pro	1126	±4	16.2K	1.5%	2.3%	45 tps	2.6s	1M	$1.25	$10.00
60	77	Claude Opus 4.1	1122	±9	1.3K	2.3%	3.0%	17 tps	3.7s	200K	$15.00	$75.00
61	44	Grok 4.1 Fast Reasoning	1119	±6	5.4K	1.5%	1.5%	58 tps	7.3s	2M	$0.20	$0.50
62	37	Claude Sonnet 4.5	1116	±6	5K	3.1%	1.4%	41 tps	1.3s	200K	$1.80	$9.00
63	56	DeepSeek V3.1 Turbo	1114	±6	4K	2.1%	0.9%	173 tps	1.3s	164K	$2.00	$3.75
64	40	DeepSeek V3.2	1113	±5	3.6K	0.8%	1.4%	83 tps	5.1s	131K	$0.43	$1.09
65	101	Gemini 2.5 Flash Lite	1112	±6	7.6K	1.7%	1.3%	210 tps	0.7s	1M	$0.10	$0.40
66	93	Qwen Max	1111	±6	7.6K	1.4%	1.5%	49 tps	1.5s	33K	$1.60	$6.40
67	95	Qwen3 32B	1111	±17	515	1.9%	3.9%	30 tps	3.1s	41K	$0.12	$0.42
68	22	GLM 5	1110	±7	1.8K	0.8%	3.4%	36 tps	2.7s	200K	$0.72	$2.55
69	84	GPT-5 Mini Minimal	1107	±10	970	3.5%	1.2%	63 tps	1.4s	400K	$0.25	$2.00
70	93	DeepSeek V3 0324 Turbo	1103	±5	4.4K	1.9%	6.3%	12 tps	2.4s	164K	$0.73	$1.79
71	121	Qwen3 32B Fast	1098	±8	9K	1.0%	11.6%	30 tps	3.1s	41K	$0.10	$0.25
72	86	DeepSeek V3.1 Chat	1097	±7	1.9K	2.3%	2.8%	21 tps	1.6s	131K	$0.38	$1.00
73	56	DeepSeek V3.2 Thinking	1096	±6	3.8K	0.9%	9.0%	30 tps	2.6s	131K	$0.28	$0.42
74	111	LongCat Flash Chat	1095	±7	1.7K	2.8%	0.8%	85 tps	0.9s	131K	$0.14	$0.68
75	84	Nova Experimental Chat 10-09	1093	±10	1.3K	7.4%	<0.1%	59 tps	6.1s	98K	$0	$0
76	121	QwQ 32B	1091	±5	9.9K	0.9%	5.4%	41 tps	2.1s	16K	$0.43	$0.56
77	33	Kimi K2.5	1090	±6	4.5K	0.7%	6.5%	33 tps	1.7s	262K	$0.34	$2.57
78	86	Nemotron 3 Nano (Thinking)	1089	±9	1.5K	0.7%	2.0%	200 tps	0.5s	256K	$0	$0
79	62	GPT-5.1 Instant	1085	±6	3.7K	1.1%	1.3%	50 tps	1.9s	400K	$1.25	$10.00
80	106	DeepSeek V3 0324	1084	±4	5.7K	1.4%	5.8%	12 tps	2.7s	164K	$0.38	$0.93
81	52	GPT-5	1083	±5	7.6K	2.2%	3.1%	78 tps	23.1s	400K	$1.25	$9.67
82	86	Claude Sonnet 4	1083	±5	12K	1.6%	1.8%	49 tps	1.3s	200K	$3.00	$15.00
83	60	MiniMax M2.1	1080	±6	5.2K	0.6%	2.1%	66 tps	2.6s	205K	$0.30	$1.20
84	159	Qwen Turbo	1079	±8	3.9K	1.4%	<0.1%	53 tps	1.1s	1M	$0.05	$0.20
85	80	GPT-5 (Minimal)	1077	±5	3K	3.6%	<0.1%	67 tps	1.4s	400K	$1.25	$10.00
86	48	Grok 4 Fast Reasoning	1077	±6	3.3K	2.8%	2.1%	102 tps	3.1s	2M	$0.30	$0.75
87	21	Claude Opus 4	1077	±13	920	2.6%	<0.1%	25 tps	1.5s	200K	$15.00	$75.00
88	121	NVIDIA Llama 3.3 Nemotron Super 49B v1.5	1076	±12	755	1.9%	2.0%	50 tps	0.6s	131K	$0.09	$0.33
89	52	Claude Haiku 4.5	1076	±8	4.2K	2.2%	1.1%	100 tps	0.9s	200K	$1.00	$5.00
90	52	Grok 4 Fast Non-Reasoning	1075	±6	2.9K	3.3%	1.5%	93 tps	0.6s	2M	$0.27	$0.67
91	95	DeepSeek-R1 Turbo	1075	±6	1.9K	2.4%	2.6%	29 tps	1.8s	64K	$2.85	$4.75
92	56	Gemini 3.1 Flash Lite Preview Thinking	1071	±13	560	1.8%	1.7%	75 tps	4.7s	1M	$0.25	$1.50
93	68	Grok 4	1070	±4	13.8K	1.6%	3.9%	29 tps	11.1s	256K	$3.00	$15.00
94	95	Gemini 2.5 Flash	1068	±4	11.2K	1.2%	1.3%	2 tps	3.7s	1M	$0.30	$2.50
95	56	MiniMax M2.1 Lightning	1067	±12	855	0.6%	1.7%	52 tps	2.1s	205K	$0.30	$2.40
96	292	AFM 4.5B	1067	±6	2.1K	1.6%	<0.1%	81 tps	0.3s	66K	$0.05	$0.20
97	79	Qwen3 Max Thinking Preview	1067	±6	3.1K	1.4%	3.1%	40 tps	2.1s	256K	$1.20	$6.00
98	108	GPT-5 Mini Low	1067	±11	755	4.4%	<0.1%	69 tps	3.2s	400K	$0.25	$2.00
99	71	Gemini 2.5 Flash Lite Preview 0925	1066	±6	3.3K	2.8%	1.2%	209 tps	0.7s	1M	$0.25	$0.35
100	124	Qwen3 235B A22B Thinking 2507	1065	±7	1.8K	1.9%	2.5%	53 tps	1.6s	131K	$0.59	$5.70
101	44	Kimi K2 Thinking Turbo	1065	±6	3K	1.9%	2.0%	75 tps	1.4s	262K	$1.15	$8.00
102	65	Mistral Large 3	1064	±7	1.8K	2.2%	2.1%	51 tps	1.0s	256K	$0.50	$1.50
103	118	GPT-4.1 mini	1062	±5	5.5K	1.8%	1.1%	67 tps	0.9s	1M	$0.34	$1.60
104	81	OpenAI o3-pro	1061	±14	1.3K	2.7%	5.2%	22 tps	70.8s	200K	$20.00	$80.00
105	133	Solar Pro 2 250710	1060	±5	4.8K	1.5%	<0.1%	9 tps	N/A	66K	$0.50	$0.50
106	106	Grok 3	1054	±6	7.1K	1.7%	1.5%	53 tps	0.6s	1M	$3.67	$18.33
107	95	Kimi K2 Thinking	1054	±9	1.9K	3.8%	4.2%	61 tps	5.9s	262K	$0.24	$1.03
108	71	DeepSeek V3.1	1053	±13	1.8K	1.6%	0.8%	197 tps	0.4s	164K	$0.55	$1.60
109	44	DeepSeek V3.1 Terminus Chat	1053	±6	2.6K	2.6%	3.4%	27 tps	1.5s	131K	$0.86	$1.80
110	133	Gemini 2.5 Pro Preview 0605	1051	±12	655	<0.1%	<0.1%	0 tps	3.7s	1M	$1.25	$10.00
111	126	Qwen3 30B A3B	1051	±7	3.9K	1.3%	5.1%	163 tps	1.0s	41K	$0.06	$0.21
112	65	DeepSeek V3.2 Exp Chat	1047	±9	2.2K	3.1%	2.6%	29 tps	1.5s	131K	$0.27	$0.39
113	62	MiniMax M2	1046	±6	3.8K	1.9%	2.2%	39 tps	2.3s	205K	$0.21	$0.85
114	119	ERNIE 4.5 300B A47B	1046	±6	5.3K	1.3%	4.7%	23 tps	2.3s	123K	$0.28	$1.10
115	133	GPT-4.1 nano	1046	±8	5.1K	2.0%	0.6%	175 tps	0.5s	1M	$0.10	$0.40
116	241	OLMo 3 7B Think	1045	±12	710	1.4%	4.2%	77 tps	0.4s	66K	$0.12	$0.20
117	48	Claude Sonnet 4 (Thinking)	1044	±5	8.4K	2.3%	1.5%	52 tps	1.5s	200K	$3.00	$13.67
118	71	Gemini 2.5 Flash Thinking	1042	±5	6.5K	1.5%	2.2%	88 tps	6.4s	1M	$0.30	$2.50
119	182	Gemini 2.5 Flash Preview Thinking	1041	±16	620	1.6%	<0.1%	26 tps	1.8s	1M	$0.15	$1.76
120	71	Qwen3.5 397B A17B	1040	±10	1.4K	1.4%	4.3%	57 tps	1.4s	256K	$0.52	$3.00
121	119	GLM 4.7 FP8	1039	±9	515	1.0%	6.9%	40 tps	1.3s	200K	$0.30	$1.20
122	106	DeepSeek V3.1 Terminus Thinking	1035	±11	1.4K	2.8%	5.9%	27 tps	1.8s	131K	$0.56	$1.68
123	113	Mistral Medium	1035	±5	3.6K	1.8%	1.8%	48 tps	0.6s	33K	$1.48	$4.55
124	147	GLM 4.5 Air	1035	±7	3.2K	2.3%	<0.1%	22 tps	1.4s	131K	$0.10	$0.38
125	65	GLM 4.6	1030	±8	2.6K	2.8%	5.4%	39 tps	1.5s	200K	$0.42	$1.66
126	86	Qwen3 235B A22B	1030	±9	3.1K	1.6%	5.3%	71 tps	0.9s	41K	$0.23	$0.63
127	95	DeepSeek V3.2 Exp Thinking	1029	±11	1.4K	0.7%	7.2%	26 tps	3.0s	131K	$0.28	$0.42
128	68	GLM 4.7	1026	±6	4.5K	0.8%	5.8%	40 tps	1.5s	200K	$0.77	$1.73
129	71	GPT-5 Mini	1025	±6	3.2K	2.0%	2.6%	66 tps	14.2s	400K	$0.25	$2.00
130	314	Weather	1025	±19	580	4.1%	<0.1%	36 tps	1.1s	32K	$0	$0
131	126	Qwen3 VL 235B A22B Thinking	1024	±11	1.6K	4.2%	4.3%	47 tps	3.0s	127K	$0.47	$3.31
132	159	Gemini 2.5 Pro Preview 0325	1023	±18	735	2.6%	<0.1%	3 tps	16.6s	1M	$1.25	$10.00
133	143	Gemini 2.0 Flash	1022	±7	2.5K	2.5%	<0.1%	76 tps	0.5s	1M	$0.14	$0.56
134	153	Qwen 2.5 32B Instruct	1019	±8	1.4K	1.8%	2.5%	48 tps	1.0s	131K	$0.21	$0.25
135	113	GLM 4.5	1019	±6	2.5K	1.6%	3.7%	46 tps	1.4s	131K	$0.43	$1.63
136	71	Seed 1.8 251228	1018	±6	4.4K	1.0%	3.7%	41 tps	2.1s	256K	$0.25	$2.00
137	139	GLM 4.6V	1018	±12	1.6K	1.2%	6.4%	21 tps	1.8s	128K	$0.38	$0.90
138	148	Qwen3 30B A3B Thinking 2507	1017	±9	2.2K	1.8%	0.5%	124 tps	1.2s	131K	$0.16	$1.70
139	56	Claude Opus 4.1 (Thinking)	1017	±8	1.5K	1.3%	<0.1%	20 tps	3.9s	200K	$15.00	$75.00
140	133	Kimi K2 0905	1013	±11	2.1K	3.7%	4.0%	30 tps	1.4s	262K	$0.63	$2.39
141	126	DeepSeek V3	1013	±6	8.8K	1.3%	0.9%	69 tps	1.1s	64K	$0.59	$1.49
142	101	DeepSeek V3 (Turbo)	1013	±12	705	1.4%	1.5%	32 tps	1.5s	64K	$0.40	$1.30
143	129	Qwen3 Max Thinking	1012	±6	2.1K	0.2%	13.5%	32 tps	2.3s	256K	$1.20	$6.00
144	129	Command A	1005	±5	8.6K	1.7%	2.2%	42 tps	0.8s	256K	$2.00	$7.33
145	143	Seed 1.6 250615	1005	±20	880	2.2%	3.1%	46 tps	2.2s	256K	$0.25	$2.00
146	213	Claude Haiku 3.5	1005	±12	1.5K	3.0%	0.8%	40 tps	2.8s	200K	$0.80	$4.00
147	133	DeepSeek V3.2 Speciale	1003	±10	1.3K	2.2%	6.0%	43 tps	1.4s	131K	$0.84	$1.52
148	113	Kimi K2 Fast	1003	±4	10K	1.8%	0.8%	365 tps	0.5s	131K	$1.00	$3.00
149	113	Gemini 2.5 Flash Lite Thinking	1003	±8	3.7K	2.4%	1.0%	118 tps	4.4s	1M	$0.03	$0.13
150	133	Qwen3 14B	1002	±6	3.6K	1.6%	1.7%	109 tps	0.8s	41K	$0.04	$0.15
151	148	DeepSeek-R1	1001	±6	5K	1.7%	0.8%	133 tps	0.6s	64K	$0.91	$3.07
152	157	Qwen3 Next 80B A3B Thinking	1000	±7	3.2K	3.0%	0.6%	175 tps	1.3s	256K	$0.21	$2.26
153	133	DeepSeek-R1 0528	998	±4	4.9K	1.5%	1.3%	93 tps	0.5s	64K	$1.60	$3.67
154	292	GPT-5 Nano Minimal	992	±16	515	4.6%	<0.1%	88 tps	0.8s	400K	$0.05	$0.40
155	161	Qwen3 8B	992	±8	3.1K	1.6%	2.4%	61 tps	1.4s	41K	$0.02	$0.07
156	71	MiniMax M2.5 FP8	988	±19	525	1.9%	3.6%	33 tps	1.7s	205K	$0.45	$1.75
157	143	Gemini 2.0 Flash Lite	988	±6	4.1K	2.6%	<0.1%	42 tps	0.5s	1M	$0.08	$0.30
158	84	Claude Sonnet 3.7 (Thinking)	983	±6	4.8K	2.1%	<0.1%	41 tps	2.6s	200K	$3.00	$15.00
159	200	K2 Think	982	±11	895	0.6%	<0.1%	418 tps	2.8s	N/A	$0	$0
160	153	OpenAI o1	981	±5	9.1K	1.7%	4.2%	92 tps	5.5s	200K	$15.00	$60.00
161	161	Llama 4 Maverick	980	±6	7.3K	1.8%	1.2%	88 tps	2.4s	1M	$0.23	$0.83
162	95	Gemini 2.5 Flash Lite Thinking Preview 0925	978	±7	2.2K	2.5%	1.5%	152 tps	3.0s	1M	$0.10	$0.40
163	182	Fauna Fox	977	±6	2K	1.7%	<0.1%	194 tps	0.3s	128K	$0.04	$0.15
164	124	Kimi K2 0905 Turbo	972	±7	3.2K	3.9%	0.7%	373 tps	0.5s	262K	$1.70	$6.50
165	79	MiniMax M2.5 Lightning	972	±17	935	1.1%	1.5%	51 tps	2.0s	205K	$0.60	$2.40
166	165	Qwen3 4B	970	±8	3.1K	2.7%	1.9%	94 tps	1.5s	128K	$0.01	$0.01
167	148	OpenAI o4-mini-high	966	±4	9.3K	1.8%	1.9%	117 tps	15.9s	200K	$1.10	$4.40
168	86	Amazon Nova 2 Lite	966	±9	1.6K	3.0%	1.0%	137 tps	0.6s	300K	$0.35	$2.95
169	175	OpenAI o3-mini-low	963	±8	8.8K	1.9%	0.7%	139 tps	1.5s	200K	$1.10	$4.40
170	129	DeepSeek V3.1 Thinking	956	±10	2.2K	2.4%	7.1%	18 tps	1.8s	131K	$0.23	$0.75
171	270	Solar Pro 2 250710 (Reasoning)	955	±7	2.3K	2.3%	<0.1%	9 tps	N/A	66K	$0.50	$0.50
172	170	Llama 3.1 8B Turbo	954	±20	685	2.1%	2.1%	650 tps	0.5s	128K	$0.13	$0.14
173	170	Mistral Small 3.2 24B	953	±9	1.4K	1.8%	2.8%	141 tps	0.7s	33K	$0.02	$0.08
174	177	Mistral Small 3.1 24B Instruct	949	±16	745	2.0%	7.5%	15 tps	2.4s	131K	$0.06	$0.18
175	277	Grok 2	949	±16	650	0.8%	<0.1%	55 tps	1.1s	131K	$2.00	$10.00
176	165	DeepSeek R1T2 Chimera	947	±20	620	2.4%	3.0%	28 tps	1.8s	164K	$0.13	$0.45
177	160	Llama 4 Scout	941	±7	6.9K	1.5%	0.6%	88 tps	5.1s	131K	$0.18	$0.46
178	179	GLM 4.7 Flash	939	±11	1.1K	1.3%	5.8%	61 tps	2.8s	128K	$0.07	$0.39
179	186	Grok 3 Mini Fast	939	±11	3.9K	2.3%	1.6%	44 tps	0.5s	131K	$0.60	$4.00
180	253	R1 1776	938	±10	3.1K	0.9%	<0.1%	61 tps	1.0s	128K	$2.00	$8.00
181	157	Cogito v2.1 671B	937	±15	885	1.7%	0.8%	85 tps	0.5s	128K	$1.25	$1.25
182	177	Llama 3 70B Turbo	935	±14	1K	1.4%	<0.1%	31 tps	0.0s	8K	$0.73	$0.83
183	148	OpenAI o3	935	±5	4.3K	1.7%	0.9%	85 tps	6.8s	128K	$7.33	$29.33
184	161	DeepSeek Prover v2	933	±17	825	2.4%	5.2%	14 tps	1.3s	164K	$0.40	$1.56
185	214	Llama 3.3 70B Instruct Turbo	931	±27	505	3.8%	2.0%	78 tps	1.0s	131K	$0.88	$0.88
186	201	Gemma 3 27B IT	930	±15	655	2.2%	2.0%	60 tps	0.8s	128K	$0.17	$0.29
187	157	GPT-5 Nano	928	±10	1.8K	3.0%	3.2%	113 tps	20.9s	400K	$0.05	$0.40
188	170	Kimi K2 0711	928	±9	3.2K	2.2%	1.6%	29 tps	1.3s	131K	$0.72	$2.60
189	253	Magistral Medium	927	±16	530	5.4%	<0.1%	95 tps	0.5s	41K	$2.00	$5.00
190	139	OpenAI o4-mini	925	±8	4K	2.3%	1.4%	97 tps	7.0s	128K	$1.10	$4.40
191	209	Seed 1.6 Flash 250715	922	±16	580	2.5%	2.5%	108 tps	1.6s	256K	$0.07	$0.30
192	214	OpenAI o3-mini-high	922	±6	7.5K	2.0%	2.4%	231 tps	10.5s	200K	$1.10	$4.40
193	177	OpenAI o3-mini	921	±6	9K	1.9%	0.8%	143 tps	3.3s	200K	$1.10	$4.40
194	214	Gemma 3 12B	921	±18	635	3.1%	4.2%	73 tps	0.8s	131K	$0.05	$0.12
195	219	NVIDIA Llama 3.3 Nemotron Super 49B v1	918	±15	920	1.1%	<0.1%	13 tps	N/A	131K	$0.07	$0.20
196	186	Jamba 1.6 Large	915	±18	660	1.5%	2.0%	59 tps	1.2s	256K	$1.33	$5.33
197	200	Claude Sonnet 3.5	914	±14	830	2.4%	1.0%	40 tps	2.7s	200K	$3.00	$15.00
198	113	GLM 4.5 AirX	913	±23	540	1.8%	3.3%	75 tps	1.2s	131K	$1.10	$4.50
199	314	DeepSeek-R1 0528 Qwen3 8B	912	±5	3.4K	2.3%	<0.1%	45 tps	2.4s	128K	$0.05	$0.09
200	211	Gemini 1.5 Pro	912	±15	580	2.5%	<0.1%	15 tps	0.0s	2M	$0.78	$3.13
201	186	Grok 3 Mini	908	±9	3.8K	2.3%	1.2%	43 tps	0.5s	131K	$0.30	$0.50
202	214	Qwen 2.5 7B	901	±19	490	4.9%	3.7%	40 tps	1.9s	131K	$0.08	$0.27
203	194	Llama 3.3 70B	900	±12	1.1K	3.0%	0.3%	500 tps	0.5s	8K	$0.48	$0.66
204	170	Devstral Medium	899	±10	995	1.5%	1.5%	77 tps	0.6s	131K	$0.40	$2.00
205	186	GLM 4.6V Flash	899	±15	1.3K	2.3%	3.7%	64 tps	2.1s	128K	$0.04	$0.40
206	186	Gemma 3n E4B	892	±10	2K	2.6%	2.0%	30 tps	0.5s	8K	$0.01	$0.02
207	241	GPT-5 Mini High	891	±10	1.4K	2.8%	<0.1%	33 tps	3.9s	400K	$0.25	$2.00
208	165	Pixtral Large	890	±12	640	4.5%	2.5%	57 tps	1.3s	128K	$1.50	$4.50
209	292	NVIDIA Llama 3.1 Nemotron Ultra 253B v1	888	±22	575	0.9%	<0.1%	40 tps	0.8s	128K	$0.30	$0.90
210	265	Llama 3.1 405B Instruct Turbo	885	±22	560	3.4%	<0.1%	26 tps	0.8s	131K	$3.50	$3.50
211	277	GLM Z1 32B	885	±14	1.1K	2.2%	<0.1%	18 tps	9.3s	33K	$0.09	$0.11
212	277	Wikipedia	882	±10	2.8K	3.7%	<0.1%	47 tps	2.1s	32K	$0	$0
213	179	Switchpoint Router	876	±16	675	1.5%	1.7%	71 tps	4.9s	131K	$0.85	$3.40
214	233	Llama 3.1 70B Instruct Turbo	869	±19	995	2.0%	<0.1%	110 tps	0.8s	128K	$0.88	$0.88
215	229	ERNIE 4.5 21B A3B Thinking	866	±16	685	2.8%	1.8%	87 tps	1.5s	120K	$0.07	$0.28
216	324	Solar Pro 3	856	±20	520	1.0%	2.0%	99 tps	1.3s	131K	$0.15	$0.60
217	209	Llama 3.3 Swallow 70B Instruct	854	±18	890	1.1%	1.4%	153 tps	1.3s	131K	$0.13	$0.39
218	200	NVIDIA Llama 3.1 Nemotron 70B	851	±19	1.3K	1.1%	<0.1%	9 tps	0.1s	128K	$0.33	$0.39
219	229	Magistral Medium 2509	849	±16	990	3.9%	4.0%	58 tps	0.9s	131K	$2.00	$5.00
220	194	Magistral Small 2506	847	±14	1.3K	1.9%	1.6%	156 tps	0.5s	40K	$0.37	$1.10
221	374	Cogito V2 671B	839	±13	1.3K	3.0%	<0.1%	41 tps	0.6s	164K	$1.25	$1.25
222	161	Mistral Small 3.1	835	±17	675	1.5%	7.4%	13 tps	2.6s	32K	$0.17	$0.28
223	209	Qwen 2.5 14B Instruct	830	±24	570	1.7%	2.4%	40 tps	1.6s	1M	$0.40	$1.61
224	270	AFM 4.5B Preview	830	±22	875	2.2%	<0.1%	32 tps	0.0s	66K	$0	$0
225	265	Magistral Small 2509	830	±23	825	5.7%	2.7%	116 tps	0.6s	131K	$0.50	$1.50
226	179	Inception Mercury	829	±10	2K	1.5%	0.4%	257 tps	1.1s	32K	$0.25	$1.00
227	260	Hermes 4 405B Reasoning FP8	828	±11	1.3K	3.7%	3.6%	32 tps	0.8s	131K	$1.00	$3.00
228	201	Llama 3 8B	826	±17	720	1.4%	6.0%	85 tps	0.7s	8K	$0.12	$0.16
229	235	Gemma 3 4B	825	±14	755	3.2%	1.3%	138 tps	0.7s	131K	$0.02	$0.04
230	222	Jamba 1.5 Large	819	±15	690	1.4%	1.7%	48 tps	0.9s	256K	$1.50	$6.00
231	194	Llama 3.2 11B Instruct	816	±22	525	2.8%	1.5%	152 tps	0.5s	8K	$0.16	$0.16
232	241	Claude Haiku 3	813	±18	645	2.3%	0.4%	62 tps	0.5s	200K	$0.25	$1.25
233	270	Arcee AI Virtuoso-Medium	809	±21	540	0.9%	<0.1%	3 tps	N/A	131K	$0.50	$0.80
234	179	Amazon Nova Pro 1.0	807	±19	1.4K	1.7%	0.9%	96 tps	0.7s	300K	$0.80	$1.70
235	201	GPT-4o mini	803	±24	545	4.4%	2.1%	71 tps	1.7s	128K	$0.15	$0.60
236	222	Sky T1 32B Preview	797	±17	625	1.6%	7.8%	73 tps	0.6s	16K	$0.12	$0.18
237	292	Arcee AI Spotlight	796	±15	1.4K	1.8%	<0.1%	121 tps	0.4s	131K	$0.18	$0.18
238	219	Arcee AI Virtuoso-Large	791	±11	840	1.8%	<0.1%	64 tps	0.5s	131K	$0.75	$1.20
239	314	MAI-DS-R1	778	±12	1.7K	3.4%	<0.1%	73 tps	3.2s	64K	$0.10	$0.40
240	225	Command R 7B	775	±18	870	1.7%	1.1%	76 tps	0.4s	128K	$0.04	$0.15
241	399	Magistral Medium (Thinking)	774	±7	2.3K	2.7%	<0.1%	67 tps	0.8s	41K	$2.00	$5.00
242	339	Refuel LLM 2 Small	768	±20	800	2.4%	<0.1%	116 tps	0.5s	8K	$0.20	$0.20
243	246	Ministral 3B	766	±21	575	1.7%	0.8%	248 tps	0.4s	131K	$0.08	$0.08
244	229	Ministral 8B	763	±23	525	3.7%	1.4%	177 tps	0.4s	128K	$0.14	$0.14
245	225	Command R	754	±22	540	2.7%	5.8%	54 tps	0.6s	128K	$0.30	$0.99
246	235	GLM 4 32B	751	±19	740	2.0%	2.6%	40 tps	1.6s	33K	$0.14	$0.14
247	241	Arcee AI Blitz	748	±15	710	1.4%	<0.1%	6 tps	N/A	33K	$0.45	$0.75
248	246	DeepSeek-R1 Distill Llama 70B	733	±10	2.6K	2.3%	3.6%	27 tps	1.6s	32K	$0.73	$0.95
249	256	Gemma 3 1B	733	±21	670	2.9%	0.6%	176 tps	1.0s	33K	$0.06	$0.10
250	214	C4AI Aya Expanse 32B	702	±22	825	1.8%	1.5%	43 tps	0.5s	128K	$0.50	$1.50
251	225	GPT-3.5 Turbo 16k	699	±17	690	0.7%	<0.1%	22 tps	0.6s	16K	$3.00	$4.00
252	406	DeepSeek-R1 Distill Qwen 14B	664	±14	1.7K	2.5%	<0.1%	44 tps	1.7s	64K	$0.63	$0.63
253	424	DeepSeek-R1 Distill Qwen 7B	664	±21	640	1.5%	<0.1%	0 tps	N/A	131K	$0.05	$0.10
254	430	DeepSeek-R1 Distill Qwen 1.5B	648	±17	915	2.1%	<0.1%	20 tps	0.0s	131K	$0.18	$0.18
255	274	DeepSeek-R1 Distill Qwen 32B	638	±9	1.8K	2.7%	6.2%	22 tps	1.8s	131K	$0.37	$0.39
256	287	Phi 4 Reasoning	632	±13	2K	2.2%	21.0%	29 tps	1.0s	33K	$0.06	$0.25
257	428	DeepSeek-R1 Distill Llama 8B	624	±20	1.1K	3.1%	<0.1%	17 tps	N/A	32K	$0.04	$0.04
258	284	MiniMax M1	570	±10	3K	1.3%	<0.1%	31 tps	2.8s	1M	$0.55	$2.20
259	291	Phi 4 Mini Reasoning	545	±12	2.3K	3.1%	9.7%	30 tps	0.9s	128K	$0.07	$0.30
260	281	MythoMax L2 13B	466	±30	520	4.6%	1.2%	22 tps	1.1s	4K	$0.18	$0.18

Show Less