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

1504

Claude Opus 4.6 (Thinking)

1445

Claude Opus 4.6

1371

GPT-5.4

1364

Claude Sonnet 4.6

1359

Gemini 3.1 Pro

1324

Claude Sonnet 4.6 (Thinking)

1282

Gemini 3 Pro

1280

Claude Opus 4.5 (Thinking)

1278

GPT-5.1

1273

GPT-5.1 (High)

1266

Gemini 3 Pro (Low)

1264

Claude Sonnet 4.5 (Thinking)

1254

GPT-5.2 Instant

1231

GLM 5

1228

Claude Sonnet 4 (Thinking)

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)	1504	±9	3.2K	1.5%	2.5%	56 tps	1.6s	200K	$5.00	$25.00
2	2	Claude Opus 4.6	1445	±8	4.3K	1.2%	2.1%	48 tps	1.7s	200K	$5.00	$25.00
3	2	GPT-5.4	1371	±13	1.1K	1.3%	2.6%	55 tps	0.8s	1M	$2.50	$15.00
4	4	Claude Sonnet 4.6	1364	±8	3K	1.1%	1.6%	47 tps	1.2s	200K	$3.00	$15.00
5	6	Gemini 3.1 Pro	1359	±9	5.8K	2.3%	3.5%	35 tps	4.1s	1M	$2.00	$12.00
6	5	Claude Sonnet 4.6 (Thinking)	1324	±9	3K	2.6%	4.7%	57 tps	1.1s	200K	$3.00	$15.00
7	10	Gemini 3 Pro	1282	±4	37.7K	3.1%	2.1%	50 tps	3.6s	1M	$2.00	$12.00
8	7	Claude Opus 4.5 (Thinking)	1280	±4	23K	2.2%	1.8%	49 tps	1.4s	200K	$5.00	$25.00
9	8	GPT-5.1	1278	±5	8.5K	4.7%	2.3%	71 tps	1.4s	400K	$1.42	$11.33
10	8	GPT-5.1 (High)	1273	±4	16.6K	4.0%	3.2%	76 tps	6.9s	400K	$1.25	$10.00
11	14	Gemini 3 Pro (Low)	1266	±5	8.4K	4.6%	2.4%	51 tps	3.5s	1M	$2.00	$12.00
12	10	Claude Sonnet 4.5 (Thinking)	1264	±2	25.1K	4.5%	1.9%	44 tps	1.1s	200K	$3.00	$15.00
13	10	GPT-5.2 Instant	1254	±5	9K	3.9%	1.7%	52 tps	2.0s	400K	$1.75	$14.00
14	22	GLM 5	1231	±12	2.3K	2.5%	3.4%	36 tps	2.7s	200K	$0.72	$2.55
15	48	Claude Sonnet 4 (Thinking)	1228	±6	5.2K	3.4%	1.5%	52 tps	1.5s	200K	$3.00	$13.67
16	17	Gemini 3 Flash Preview	1226	±6	5.3K	4.2%	1.3%	138 tps	1.4s	1M	$0.50	$3.00
17	14	Gemini 3 Flash Preview Thinking	1225	±6	13.8K	3.4%	1.6%	3 tps	6.2s	1M	$0.50	$3.00
18	17	GPT-5.2 (High)	1221	±4	19.4K	3.1%	6.7%	18 tps	16.3s	400K	$1.75	$14.00
19	37	Claude Sonnet 4.5	1219	±5	13.7K	6.6%	1.4%	41 tps	1.3s	200K	$1.80	$9.00
20	16	GPT-5.2	1219	±6	6.2K	3.8%	4.1%	18 tps	2.7s	400K	$1.75	$14.00
21	17	Grok 4.20 Beta Reasoning	1209	±21	850	1.7%	1.1%	77 tps	4.5s	2M	$2.00	$5.50
22	17	Claude Opus 4.5	1207	±5	6.6K	3.6%	1.5%	45 tps	1.5s	200K	$5.00	$25.00
23	56	Gemini 3.1 Flash Lite Preview Thinking	1199	±13	950	3.1%	1.7%	75 tps	4.7s	1M	$0.25	$1.50
24	22	GPT-5 Chat	1193	±3	23.9K	6.8%	1.3%	95 tps	0.9s	400K	$1.25	$10.00
25	13	GPT-5.3 Instant	1191	±8	2.2K	1.8%	0.9%	63 tps	0.8s	400K	$1.75	$14.00
26	42	GPT-5.2 (Extra High)	1189	±6	6.7K	3.5%	13.2%	17 tps	20.5s	400K	$1.75	$14.00
27	26	GPT-5 (High)	1171	±4	12K	3.7%	4.5%	81 tps	35.9s	400K	$1.25	$10.00
28	32	Gemini 2.5 Pro High	1169	±4	16.8K	7.8%	1.5%	48 tps	2.3s	1M	$1.25	$10.00
29	33	Kimi K2.5	1169	±6	5.3K	2.8%	6.5%	33 tps	1.7s	262K	$0.34	$2.57
30	44	Gemini 2.5 Pro	1168	±4	19.1K	9.1%	2.3%	45 tps	2.6s	1M	$1.25	$10.00
31	86	Seed 2.0 Lite (Medium)	1166	±14	575	2.5%	6.6%	33 tps	1.6s	256K	$0.25	$2.00
32	71	MiniMax M2.5 FP8	1162	±17	575	3.4%	3.6%	33 tps	1.7s	205K	$0.45	$1.75
33	29	Qwen3 VL 235B A22B Instruct	1161	±6	4.5K	8.8%	3.1%	75 tps	1.9s	129K	$0.37	$1.81
34	44	Kimi K2 Thinking Turbo	1160	±8	13.2K	3.5%	2.0%	75 tps	1.4s	262K	$1.15	$8.00
35	56	MiniMax M2.1 Lightning	1157	±13	970	1.0%	1.7%	52 tps	2.1s	205K	$0.30	$2.40
36	71	Gemini 2.5 Flash Thinking	1153	±7	3.7K	3.6%	2.2%	88 tps	6.4s	1M	$0.30	$2.50
37	26	Claude Haiku 4.5 (Extended Thinking)	1152	±5	7K	6.6%	1.4%	115 tps	0.7s	200K	$1.00	$5.00
38	42	Qwen3 Max Instruct Preview	1150	±4	13.5K	5.8%	1.1%	31 tps	1.7s	256K	$1.43	$6.61
39	60	MiniMax M2.1	1149	±6	10.4K	4.3%	2.1%	66 tps	2.6s	205K	$0.30	$1.20
40	44	Grok 4.1 Fast Reasoning	1149	±6	21.2K	4.2%	1.5%	58 tps	7.3s	2M	$0.20	$0.50
41	40	Qwen3 235B A22B Instruct 2507	1146	±3	8.8K	12.2%	6.8%	13 tps	1.9s	262K	$0.13	$0.52
42	33	Grok 4.20 Multi Agent Beta	1143	±16	765	1.9%	1.2%	56 tps	8.8s	2M	$2.00	$6.00
43	33	Qwen3 Next 80B A3B Instruct	1141	±4	7.6K	7.7%	0.6%	84 tps	1.1s	256K	$0.20	$1.42
44	84	GPT-5 Mini Minimal	1139	±8	2.8K	9.7%	1.2%	63 tps	1.4s	400K	$0.25	$2.00
45	52	GPT-5	1138	±4	14K	7.9%	3.1%	78 tps	23.1s	400K	$1.25	$9.67
46	26	Grok 4.1 Fast Non-Reasoning	1137	±5	7.4K	6.6%	0.9%	101 tps	0.5s	2M	$0.20	$0.50
47	65	GLM 4.6	1136	±5	14.1K	4.7%	5.4%	39 tps	1.5s	200K	$0.42	$1.66
48	52	Claude Haiku 4.5	1134	±5	9.9K	6.9%	1.1%	100 tps	0.9s	200K	$1.00	$5.00
49	62	GPT-5.1 Instant	1134	±5	5.5K	5.7%	1.3%	50 tps	1.9s	400K	$1.25	$10.00
50	68	Grok 4	1130	±2	23.2K	6.4%	3.9%	29 tps	11.1s	256K	$3.00	$15.00
51	71	GPT-5 Mini	1130	±4	6.1K	7.9%	2.6%	66 tps	14.2s	400K	$0.25	$2.00
52	40	DeepSeek V3.2	1130	±5	4.4K	5.1%	1.4%	83 tps	5.1s	131K	$0.43	$1.09
53	79	MiniMax M2.5 Lightning	1128	±14	995	2.5%	1.5%	51 tps	2.0s	205K	$0.60	$2.40
54	48	Grok 4 Fast Reasoning	1125	±5	11.8K	5.5%	2.1%	102 tps	3.1s	2M	$0.30	$0.75
55	52	Qwen3.5 122B A17B	1124	±17	1.1K	3.2%	1.5%	82 tps	1.4s	256K	$0.40	$3.20
56	37	Kimi K2.5 Instant	1124	±13	1.4K	2.4%	2.9%	32 tps	3.0s	262K	$0.50	$3.00
57	81	GPT-4o	1124	±5	6.5K	6.1%	1.0%	49 tps	2.4s	128K	$3.71	$12.57
58	56	DeepSeek V3.2 Thinking	1117	±6	10K	3.8%	9.0%	30 tps	2.6s	131K	$0.28	$0.42
59	68	Qwen Plus (Aug'24)	1116	±5	8.9K	9.4%	1.4%	53 tps	1.3s	30K	$0.40	$1.20
60	29	Nova Experimental Chat 12-10	1115	±8	2.2K	4.8%	2.4%	84 tps	12.9s	98K	$0	$0
61	71	Gemini 3.1 Flash Lite Preview	1114	±27	630	2.3%	1.0%	8 tps	1.2s	1M	$0.25	$1.50
62	68	GLM 4.7	1112	±8	8.8K	4.7%	5.8%	40 tps	1.5s	200K	$0.77	$1.73
63	60	Gemini 2.5 Flash Preview 0925	1110	±4	6.7K	7.5%	1.2%	5 tps	0.9s	1M	$0.13	$0.97
64	52	Grok 4 Fast Non-Reasoning	1110	±5	7.1K	8.3%	1.5%	93 tps	0.6s	2M	$0.27	$0.67
65	106	Claude Sonnet 3.5 v2	1109	±7	2.9K	8.2%	<0.1%	46 tps	1.4s	200K	$3.00	$15.00
66	65	Mistral Large 3	1108	±7	4K	6.3%	2.1%	51 tps	1.0s	256K	$0.50	$1.50
67	33	Qwen3 30B A3B Instruct 2507	1108	±5	8.5K	9.7%	1.2%	55 tps	1.3s	131K	$0.13	$0.72
68	56	DeepSeek V3.1 Turbo	1106	±9	2.6K	5.1%	0.9%	173 tps	1.3s	164K	$2.00	$3.75
69	95	Gemini 2.5 Flash Lite Thinking Preview 0925	1104	±5	4.9K	7.8%	1.5%	152 tps	3.0s	1M	$0.10	$0.40
70	106	Grok 3	1102	±5	9.3K	9.3%	1.5%	53 tps	0.6s	1M	$3.67	$18.33
71	86	Claude Sonnet 4	1102	±4	18.3K	7.0%	1.8%	49 tps	1.3s	200K	$3.00	$15.00
72	44	DeepSeek V3.1 Terminus Chat	1100	±4	5.1K	9.6%	3.4%	27 tps	1.5s	131K	$0.86	$1.80
73	95	Gemini 2.5 Flash	1098	±5	21.4K	5.2%	1.3%	2 tps	3.7s	1M	$0.30	$2.50
74	179	Switchpoint Router	1097	±11	1.1K	9.5%	1.7%	71 tps	4.9s	131K	$0.85	$3.40
75	71	Seed 1.8 251228	1096	±6	4.1K	3.4%	3.7%	41 tps	2.1s	256K	$0.25	$2.00
76	106	DeepSeek V3 0324	1090	±5	9.7K	8.2%	5.8%	12 tps	2.7s	164K	$0.38	$0.93
77	113	Mistral Medium	1087	±4	5.3K	9.0%	1.8%	48 tps	0.6s	33K	$1.48	$4.55
78	62	MiniMax M2	1087	±6	16.5K	5.2%	2.2%	39 tps	2.3s	205K	$0.21	$0.85
79	48	gpt-oss-120b	1086	±4	15.1K	7.5%	0.7%	213 tps	0.5s	131K	$0.11	$0.50
80	62	Qwen3 Omni 30B A3B Instruct	1085	±14	570	6.6%	3.9%	65 tps	1.2s	66K	$0.35	$0.97
81	86	DeepSeek V3.1 Chat	1084	±6	3.7K	10.1%	2.8%	21 tps	1.6s	131K	$0.38	$1.00
82	81	Qwen3.5 27B	1082	±26	550	2.7%	3.7%	55 tps	2.6s	256K	$0.30	$2.40
83	48	Step 3.5 Flash	1079	±23	645	2.3%	2.2%	109 tps	0.6s	256K	$0.05	$0.15
84	65	DeepSeek V3.2 Exp Chat	1079	±4	4.3K	8.8%	2.6%	29 tps	1.5s	131K	$0.27	$0.39
85	93	Qwen Max	1077	±5	8.8K	9.1%	1.5%	49 tps	1.5s	33K	$1.60	$6.40
86	86	Qwen3 235B A22B	1074	±10	2.8K	14.4%	5.3%	71 tps	0.9s	41K	$0.23	$0.63
87	71	Gemini 2.5 Flash Lite Preview 0925	1070	±5	6.7K	8.6%	1.2%	209 tps	0.7s	1M	$0.25	$0.35
88	95	Qwen3 32B	1070	±18	620	7.5%	3.9%	30 tps	3.1s	41K	$0.12	$0.42
89	95	Kimi K2 Thinking	1064	±12	1.6K	6.8%	4.2%	61 tps	5.9s	262K	$0.24	$1.03
90	95	DeepSeek V3.2 Exp Thinking	1063	±8	5K	3.4%	7.2%	26 tps	3.0s	131K	$0.28	$0.42
91	118	GPT-4.1 mini	1060	±4	11.7K	6.8%	1.1%	67 tps	0.9s	1M	$0.34	$1.60
92	113	Gemini 2.5 Flash Lite Thinking	1059	±5	6.6K	9.5%	1.0%	118 tps	4.4s	1M	$0.03	$0.13
93	93	DeepSeek V3 0324 Turbo	1055	±5	9.3K	10.3%	6.3%	12 tps	2.4s	164K	$0.73	$1.79
94	71	Qwen3.5 397B A17B	1055	±11	1.6K	2.1%	4.3%	57 tps	1.4s	256K	$0.52	$3.00
95	139	Seed 2.0 Mini (Medium)	1053	±21	605	4.0%	11.9%	33 tps	1.7s	256K	$0.15	$0.60
96	111	Grok 3 Fast	1051	±17	1.1K	2.6%	1.7%	52 tps	2.4s	131K	$5.00	$25.00
97	81	OpenAI o3-pro	1048	±8	2.2K	3.5%	5.2%	22 tps	70.8s	200K	$20.00	$80.00
98	37	Qwen3 Omni 30B A3B Thinking	1047	±11	1.3K	5.9%	3.7%	67 tps	1.2s	66K	$0.97	$1.79
99	106	DeepSeek V3.1 Terminus Thinking	1047	±7	2.5K	11.6%	5.9%	27 tps	1.8s	131K	$0.56	$1.68
100	119	GLM 4.7 FP8	1046	±19	490	3.0%	6.9%	40 tps	1.3s	200K	$0.30	$1.20
101	79	Qwen3 Max Thinking Preview	1044	±5	5.1K	7.7%	3.1%	40 tps	2.1s	256K	$1.20	$6.00
102	143	Seed 1.6 250615	1042	±13	1.2K	4.8%	3.1%	46 tps	2.2s	256K	$0.25	$2.00
103	165	Pixtral Large	1042	±8	2.5K	5.1%	2.5%	57 tps	1.3s	128K	$1.50	$4.50
104	124	Kimi K2 0905 Turbo	1041	±4	6.8K	12.4%	0.7%	373 tps	0.5s	262K	$1.70	$6.50
105	143	Gemini 2.0 Flash	1038	±6	3.7K	8.9%	<0.1%	76 tps	0.5s	1M	$0.14	$0.56
106	101	Gemini 2.5 Flash Lite	1038	±5	12.8K	12.6%	1.3%	210 tps	0.7s	1M	$0.10	$0.40
107	153	OpenAI o1	1037	±15	1.2K	4.8%	4.2%	92 tps	5.5s	200K	$15.00	$60.00
108	157	GPT-5 Nano	1035	±6	3.8K	10.6%	3.2%	113 tps	20.9s	400K	$0.05	$0.40
109	101	DeepSeek V3 (Turbo)	1034	±11	1K	5.9%	1.5%	32 tps	1.5s	64K	$0.40	$1.30
110	119	ERNIE 4.5 300B A47B	1032	±6	6.1K	8.7%	4.7%	23 tps	2.3s	123K	$0.28	$1.10
111	95	DeepSeek-R1 Turbo	1032	±10	1.4K	5.5%	2.6%	29 tps	1.8s	64K	$2.85	$4.75
112	71	DeepSeek V3.1	1029	±10	1.1K	4.5%	0.8%	197 tps	0.4s	164K	$0.55	$1.60
113	129	Command A	1029	±5	11K	8.4%	2.2%	42 tps	0.8s	256K	$2.00	$7.33
114	126	DeepSeek V3	1028	±7	5.9K	5.7%	0.9%	69 tps	1.1s	64K	$0.59	$1.49
115	86	Amazon Nova 2 Lite	1027	±10	2.6K	7.9%	1.0%	137 tps	0.6s	300K	$0.35	$2.95
116	113	GLM 4.5 AirX	1020	±10	805	9.0%	3.3%	75 tps	1.2s	131K	$1.10	$4.50
117	133	GPT-4.1 nano	1020	±4	8.8K	9.7%	0.6%	175 tps	0.5s	1M	$0.10	$0.40
118	124	Qwen3 235B A22B Thinking 2507	1018	±11	1.1K	4.2%	2.5%	53 tps	1.6s	131K	$0.59	$5.70
119	148	OpenAI o3	1016	±11	1.3K	4.6%	0.9%	85 tps	6.8s	128K	$7.33	$29.33
120	129	DeepSeek V3.1 Thinking	1014	±7	3.9K	14.0%	7.1%	18 tps	1.8s	131K	$0.23	$0.75
121	139	Qwen3 VL 30B A3B Instruct	1012	±17	1K	6.5%	1.8%	80 tps	2.6s	129K	$0.18	$0.67
122	143	Gemini 2.0 Flash Lite	1011	±6	5.7K	6.9%	<0.1%	42 tps	0.5s	1M	$0.08	$0.30
123	113	Kimi K2 Fast	1006	±4	26.2K	13.8%	0.8%	365 tps	0.5s	131K	$1.00	$3.00
124	113	GLM 4.5	1002	±5	3.7K	14.3%	3.7%	46 tps	1.4s	131K	$0.43	$1.63
125	121	NVIDIA Llama 3.3 Nemotron Super 49B v1.5	1000	±16	1K	9.9%	2.0%	50 tps	0.6s	131K	$0.09	$0.33
126	139	OpenAI o4-mini	1000	±5	4.8K	10.2%	1.4%	97 tps	7.0s	128K	$1.10	$4.40
127	170	Llama 3.1 8B Turbo	998	±12	1.1K	2.8%	2.1%	650 tps	0.5s	128K	$0.13	$0.14
128	111	LongCat Flash Chat	996	±14	930	7.0%	0.8%	85 tps	0.9s	131K	$0.14	$0.68
129	133	Kimi K2 0905	991	±6	7.5K	5.6%	4.0%	30 tps	1.4s	262K	$0.63	$2.39
130	129	Qwen3 Max Thinking	990	±13	1.7K	2.3%	13.5%	32 tps	2.3s	256K	$1.20	$6.00
131	157	Cogito v2.1 671B	984	±17	715	5.9%	0.8%	85 tps	0.5s	128K	$1.25	$1.25
132	133	DeepSeek-R1 0528	983	±12	1.3K	4.6%	1.3%	93 tps	0.5s	64K	$1.60	$3.67
133	201	Gemma 3 27B IT	983	±15	905	10.4%	2.0%	60 tps	0.8s	128K	$0.17	$0.29
134	126	Qwen3 VL 235B A22B Thinking	979	±6	3.5K	11.5%	4.3%	47 tps	3.0s	127K	$0.47	$3.31
135	165	DeepSeek R1T2 Chimera	978	±10	1.1K	11.0%	3.0%	28 tps	1.8s	164K	$0.13	$0.45
136	214	Qwen 2.5 VL 32B Instruct	977	±20	850	7.6%	6.3%	43 tps	3.2s	128K	$0.35	$0.62
137	209	Seed 1.6 Flash 250715	974	±16	980	6.2%	2.5%	108 tps	1.6s	256K	$0.07	$0.30
138	222	Sky T1 32B Preview	972	±16	805	10.6%	7.8%	73 tps	0.6s	16K	$0.12	$0.18
139	177	Mistral Small 3.1 24B Instruct	966	±12	1K	10.6%	7.5%	15 tps	2.4s	131K	$0.06	$0.18
140	161	Mistral Small 3.1	960	±16	915	11.2%	7.4%	13 tps	2.6s	32K	$0.17	$0.28
141	161	Llama 4 Maverick	956	±4	11.2K	8.2%	1.2%	88 tps	2.4s	1M	$0.23	$0.83
142	121	QwQ 32B	955	±7	5K	15.3%	5.4%	41 tps	2.1s	16K	$0.43	$0.56
143	101	gpt-oss-20b	954	±5	6.1K	10.8%	0.5%	216 tps	0.5s	131K	$0.06	$0.26
144	165	Qwen3 VL 30B A3B Thinking	949	±8	1.5K	11.2%	4.5%	84 tps	2.9s	127K	$0.20	$1.47
145	177	OpenAI o3-mini	946	±6	6.7K	12.3%	0.8%	143 tps	3.3s	200K	$1.10	$4.40
146	153	Ministral 14B 3.0	945	±28	490	11.7%	2.0%	119 tps	0.5s	128K	$0.20	$0.20
147	170	Devstral Medium	945	±11	1.6K	14.7%	1.5%	77 tps	0.6s	131K	$0.40	$2.00
148	194	Llama 3.2 11B Instruct	943	±14	745	14.4%	1.5%	152 tps	0.5s	8K	$0.16	$0.16
149	126	Qwen3 30B A3B	939	±5	3.7K	12.1%	5.1%	163 tps	1.0s	41K	$0.06	$0.21
150	201	GPT-4o mini	939	±9	1.4K	9.2%	2.1%	71 tps	1.7s	128K	$0.15	$0.60
151	148	DeepSeek-R1	939	±12	1.6K	5.5%	0.8%	133 tps	0.6s	64K	$0.91	$3.07
152	86	Nemotron 3 Nano (Thinking)	938	±14	1.3K	7.6%	2.0%	200 tps	0.5s	256K	$0	$0
153	139	GLM 4.6V	938	±11	2.5K	6.1%	6.4%	21 tps	1.8s	128K	$0.38	$0.90
154	148	OpenAI o4-mini-high	937	±6	6K	14.9%	1.9%	117 tps	15.9s	200K	$1.10	$4.40
155	175	OpenAI o3-mini-low	937	±4	6.1K	13.6%	0.7%	139 tps	1.5s	200K	$1.10	$4.40
156	133	Qwen3 14B	933	±11	2.7K	17.1%	1.7%	109 tps	0.8s	41K	$0.04	$0.15
157	121	Qwen3 32B Fast	932	±5	4.5K	12.9%	11.6%	30 tps	3.1s	41K	$0.10	$0.25
158	265	Qwen 2.5 VL 72B Instruct	929	±12	1.2K	7.9%	5.3%	25 tps	3.7s	128K	$1.01	$2.79
159	209	Qwen 2.5 14B Instruct	928	±13	910	11.7%	2.4%	40 tps	1.6s	1M	$0.40	$1.61
160	133	DeepSeek V3.2 Speciale	924	±12	1.6K	6.3%	6.0%	43 tps	1.4s	131K	$0.84	$1.52
161	201	Devstral Small	924	±16	570	12.3%	2.4%	180 tps	0.6s	131K	$0.10	$0.30
162	194	Magistral Small 2506	920	±15	2K	6.9%	1.6%	156 tps	0.5s	40K	$0.37	$1.10
163	179	Inception Mercury	919	±10	2.8K	11.5%	0.4%	257 tps	1.1s	32K	$0.25	$1.00
164	148	Qwen3 30B A3B Thinking 2507	919	±10	1.3K	3.6%	0.5%	124 tps	1.2s	131K	$0.16	$1.70
165	229	Magistral Medium 2509	918	±8	2.1K	11.3%	4.0%	58 tps	0.9s	131K	$2.00	$5.00
166	153	Qwen 2.5 32B Instruct	916	±9	1.9K	18.0%	2.5%	48 tps	1.0s	131K	$0.21	$0.25
167	179	Amazon Nova Pro 1.0	916	±16	2.1K	10.3%	0.9%	96 tps	0.7s	300K	$0.80	$1.70
168	186	Mistral Small 3.2 24B Instruct	915	±22	525	9.5%	1.9%	113 tps	1.1s	131K	$0.02	$0.08
169	214	Llama 3.3 70B Instruct Turbo	914	±24	640	11.7%	2.0%	78 tps	1.0s	131K	$0.88	$0.88
170	160	Llama 4 Scout	911	±6	8K	9.6%	0.6%	88 tps	5.1s	131K	$0.18	$0.46
171	179	Baichuan-M2-32B	911	±25	505	13.7%	<0.1%	32 tps	3.3s	131K	$0.07	$0.07
172	170	Kimi K2 0711	911	±8	3.2K	9.2%	1.6%	29 tps	1.3s	131K	$0.72	$2.60
173	170	Mistral Small 3.2 24B	911	±10	2K	12.4%	2.8%	141 tps	0.7s	33K	$0.02	$0.08
174	214	OpenAI o3-mini-high	908	±14	1.1K	6.5%	2.4%	231 tps	10.5s	200K	$1.10	$4.40
175	246	DeepSeek-R1 Distill Llama 70B	907	±23	535	7.0%	3.6%	27 tps	1.6s	32K	$0.73	$0.95
176	186	Gemma 3n E4B	905	±10	2.6K	8.4%	2.0%	30 tps	0.5s	8K	$0.01	$0.02
177	201	ERNIE 4.5 VL 424B A47B	905	±12	805	7.5%	4.9%	36 tps	3.5s	123K	$0.42	$1.25
178	209	Llama 3.3 Swallow 70B Instruct	904	±8	1.6K	15.2%	1.4%	153 tps	1.3s	131K	$0.13	$0.39
179	186	Grok 3 Mini	903	±5	6K	12.8%	1.2%	43 tps	0.5s	131K	$0.30	$0.50
180	157	Qwen3 Next 80B A3B Thinking	903	±7	4.9K	11.2%	0.6%	175 tps	1.3s	256K	$0.21	$2.26
181	161	Qwen3 8B	902	±12	2K	17.8%	2.4%	61 tps	1.4s	41K	$0.02	$0.07
182	186	Gemma 3 27B	902	±18	615	13.4%	1.8%	35 tps	1.1s	66K	$0.06	$0.10
183	186	Grok 3 Mini Fast	897	±7	5.2K	14.9%	1.6%	44 tps	0.5s	131K	$0.60	$4.00
184	186	Jamba 1.6 Large	895	±11	880	9.7%	2.0%	59 tps	1.2s	256K	$1.33	$5.33
185	194	Llama 3.3 70B	893	±10	2.2K	9.2%	0.3%	500 tps	0.5s	8K	$0.48	$0.66
186	235	GLM 4 32B	893	±12	1.2K	11.1%	2.6%	40 tps	1.6s	33K	$0.14	$0.14
187	214	C4AI Aya Expanse 32B	889	±11	1.3K	10.0%	1.5%	43 tps	0.5s	128K	$0.50	$1.50
188	179	GLM 4.7 Flash	887	±13	845	2.9%	5.8%	61 tps	2.8s	128K	$0.07	$0.39
189	246	Mixtral 8x22B	880	±23	465	12.3%	1.2%	140 tps	0.6s	64K	$2.00	$6.00
190	186	Jamba 1.7 Large	877	±17	620	15.1%	1.3%	58 tps	1.0s	256K	$1.33	$5.33
191	214	Gemma 3 12B	874	±15	910	11.2%	4.2%	73 tps	0.8s	131K	$0.05	$0.12
192	225	Command R	872	±16	770	12.5%	5.8%	54 tps	0.6s	128K	$0.30	$0.99
193	165	Qwen3 4B	871	±7	3.3K	16.3%	1.9%	94 tps	1.5s	128K	$0.01	$0.01
194	256	Solar Mini 250422	869	±15	640	16.3%	1.8%	90 tps	1.7s	33K	$0.15	$0.15
195	229	Ministral 8B	868	±15	800	13.5%	1.4%	177 tps	0.4s	128K	$0.14	$0.14
196	246	Mixtral 8x22B Instruct	866	±31	570	10.2%	1.8%	142 tps	0.7s	66K	$0.45	$0.45
197	274	Moonshot V1 128k Vision	862	±17	585	7.1%	3.1%	44 tps	3.8s	131K	$2.00	$5.00
198	194	Mistral Small 3 24B Instruct	858	±18	585	12.7%	2.6%	77 tps	0.6s	33K	$0.07	$0.14
199	179	Qwen 2.5 72B	854	±26	535	11.6%	1.2%	96 tps	1.2s	131K	$0.14	$0.26
200	222	Rnj-1 Instruct	853	±24	590	7.8%	0.6%	103 tps	0.3s	33K	$0.15	$0.15
201	240	Hermes 4 405B FP8	850	±16	500	13.0%	3.5%	31 tps	0.9s	131K	$0.52	$1.73
202	222	Jamba 1.5 Large	844	±13	915	12.0%	1.7%	48 tps	0.9s	256K	$1.50	$6.00
203	260	Hermes 4 405B Reasoning FP8	844	±12	2.1K	18.8%	3.6%	32 tps	0.8s	131K	$1.00	$3.00
204	265	Magistral Small 2509	844	±26	745	8.0%	2.7%	116 tps	0.6s	131K	$0.50	$1.50
205	201	Llama 3 8B	840	±19	835	15.7%	6.0%	85 tps	0.7s	8K	$0.12	$0.16
206	186	GLM 4.6V Flash	837	±9	2K	9.0%	3.7%	64 tps	2.1s	128K	$0.04	$0.40
207	214	Krutrim 2	832	±14	560	2.6%	12.5%	33 tps	2.1s	128K	$1.00	$1.00
208	235	Command R+	828	±21	665	10.1%	2.8%	36 tps	0.7s	128K	$2.08	$9.45
209	274	Pixtral 12B	828	±11	2.2K	6.8%	2.2%	101 tps	1.2s	131K	$0.08	$0.08
210	235	Gemma 3 4B	827	±11	1.2K	9.9%	1.3%	138 tps	0.7s	131K	$0.02	$0.04
211	214	Qwen 2.5 7B	823	±15	685	11.6%	3.7%	40 tps	1.9s	131K	$0.08	$0.27
212	225	Open Mistral Nemo	818	±24	590	12.6%	1.5%	171 tps	0.5s	131K	$0.15	$0.15
213	256	Mixtral 8x7B Instruct	815	±28	510	12.1%	0.2%	79 tps	0.7s	33K	$0.23	$0.31
214	225	Command R 7B	808	±13	1.3K	12.9%	1.1%	76 tps	0.4s	128K	$0.04	$0.15
215	225	GPT-3.5 Turbo 16k	807	±11	1.1K	10.6%	<0.1%	22 tps	0.6s	16K	$3.00	$4.00
216	235	Mixtral 8x7B	801	±29	525	12.5%	2.2%	142 tps	0.6s	33K	$0.23	$0.23
217	260	Mistral Small	799	±23	465	12.3%	1.7%	142 tps	0.6s	32K	$0.43	$1.30
218	246	WizardLM-2 8x22B	795	±18	515	7.2%	11.6%	11 tps	2.5s	66K	$0.77	$0.77
219	271	Hermes 3 405B Instruct	792	±21	490	10.1%	2.3%	20 tps	1.1s	131K	$0.80	$0.80
220	265	LFM2 2.6B	787	±17	545	15.5%	6.7%	184 tps	0.4s	33K	$0.01	$0.02
221	256	Phi 4	780	±17	565	11.7%	5.1%	28 tps	1.3s	128K	$0.10	$0.32
222	246	Ministral 3B	772	±17	785	12.3%	0.8%	248 tps	0.4s	131K	$0.08	$0.08
223	260	Open Mistral 7B	770	±28	510	12.8%	0.7%	176 tps	0.4s	33K	$0.25	$0.25
224	284	MiniMax M1	769	±16	1.1K	17.9%	<0.1%	31 tps	2.8s	1M	$0.55	$2.20
225	256	Gemma 3 1B	758	±23	965	13.1%	0.6%	176 tps	1.0s	33K	$0.06	$0.10
226	201	Mistral Small 24B Instruct	752	±22	480	15.0%	1.5%	84 tps	0.4s	33K	$0.80	$0.80
227	240	GPT-3.5 Turbo Instruct	751	±21	530	10.9%	<0.1%	46 tps	1.2s	4K	$1.50	$2.00
228	271	Inflection 3 Pi	738	±21	545	11.4%	1.1%	33 tps	3.4s	8K	$2.50	$10.00
229	253	Gemma 2 27B	727	±15	585	11.4%	1.4%	44 tps	1.4s	8K	$0.80	$0.80
230	274	LFM2 8B A1B	726	±26	570	17.4%	<0.1%	142 tps	0.3s	33K	$0.01	$0.02
231	265	Inflection 3 Productivity	713	±16	600	11.8%	0.6%	50 tps	3.2s	8K	$2.50	$10.00
232	271	Mistral Large	706	±17	500	12.3%	1.5%	54 tps	0.7s	33K	$2.00	$6.00
233	265	Mixtral-8x7B Instruct v0.1	675	±39	465	12.3%	1.3%	54 tps	0.4s	33K	$0.60	$0.60
234	288	Qwen 2.5 VL 3B Instruct	670	±12	2.5K	9.2%	3.0%	44 tps	2.5s	128K	$0.21	$0.63
235	281	MythoMax L2 13B	569	±32	785	15.1%	1.2%	22 tps	1.1s	4K	$0.18	$0.18
236	285	Hunyuan A13B Instruct	485	±27	650	21.2%	2.3%	67 tps	2.0s	33K	$0.01	$0.01
237	291	Phi 4 Mini Reasoning	475	±12	1.9K	22.5%	9.7%	30 tps	0.9s	128K	$0.07	$0.30

Show Less