Leaderboard | Text

Models

Choose model family

Claude by Anthropic

Mistral by Mistral AI

Topics

Choose topic

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

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

258

Phi 4 Mini Reasoning

486

Phi 4 Reasoning

654

GPT-4o mini

679

Qwen 2.5 14B Instruct

681

Hermes 4 405B Reasoning FP8

689

Gemma 3 12B

707

MiniMax M1

709

C4AI Aya Expanse 32B

710

Switchpoint Router

724

Gemma 3 4B

726

Llama 3.3 70B

730

Command R

736

DeepSeek-R1 Distill Qwen 32B

744

Jamba 1.5 Large

755

DeepSeek-R1 Distill Llama 70B

Last updated about 1 month ago

Rank	Overall	Name	VIBE Score	Confidence Interval	Votes	Downvote %	Abort %	Speed	Latency	Context	Cost (Input)	Cost (Output)
1	291	Phi 4 Mini Reasoning	258	±22	935	7.0%	9.7%	30 tps	0.9s	128K	$0.07	$0.30
2	287	Phi 4 Reasoning	486	±32	530	2.8%	21.0%	29 tps	1.0s	33K	$0.06	$0.25
3	201	GPT-4o mini	654	±30	515	4.6%	2.1%	71 tps	1.7s	128K	$0.15	$0.60
4	209	Qwen 2.5 14B Instruct	679	±22	505	3.8%	2.4%	40 tps	1.6s	1M	$0.40	$1.61
5	260	Hermes 4 405B Reasoning FP8	681	±31	725	5.2%	3.6%	32 tps	0.8s	131K	$1.00	$3.00
6	214	Gemma 3 12B	689	±23	550	4.3%	4.2%	73 tps	0.8s	131K	$0.05	$0.12
7	284	MiniMax M1	707	±14	1.5K	1.0%	<0.1%	31 tps	2.8s	1M	$0.55	$2.20
8	214	C4AI Aya Expanse 32B	709	±22	925	1.6%	1.5%	43 tps	0.5s	128K	$0.50	$1.50
9	179	Switchpoint Router	710	±26	620	3.1%	1.7%	71 tps	4.9s	131K	$0.85	$3.40
10	235	Gemma 3 4B	724	±24	660	3.6%	1.3%	138 tps	0.7s	131K	$0.02	$0.04
11	194	Llama 3.3 70B	726	±26	735	5.2%	0.3%	500 tps	0.5s	8K	$0.48	$0.66
12	225	Command R	730	±23	605	2.4%	5.8%	54 tps	0.6s	128K	$0.30	$0.99
13	274	DeepSeek-R1 Distill Qwen 32B	736	±22	570	1.7%	6.2%	22 tps	1.8s	131K	$0.37	$0.39
14	222	Jamba 1.5 Large	744	±24	715	2.1%	1.7%	48 tps	0.9s	256K	$1.50	$6.00
15	246	DeepSeek-R1 Distill Llama 70B	755	±19	960	2.5%	3.6%	27 tps	1.6s	32K	$0.73	$0.95
16	186	Jamba 1.6 Large	761	±15	780	1.9%	2.0%	59 tps	1.2s	256K	$1.33	$5.33
17	229	Magistral Medium 2509	782	±28	550	7.6%	4.0%	58 tps	0.9s	131K	$2.00	$5.00
18	225	Command R 7B	787	±26	660	2.9%	1.1%	76 tps	0.4s	128K	$0.04	$0.15
19	179	Amazon Nova Pro 1.0	803	±13	1.2K	2.0%	0.9%	96 tps	0.7s	300K	$0.80	$1.70
20	186	Grok 3 Mini Fast	807	±14	2.4K	1.8%	1.6%	44 tps	0.5s	131K	$0.60	$4.00
21	186	Gemma 3n E4B	814	±17	1.6K	3.6%	2.0%	30 tps	0.5s	8K	$0.01	$0.02
22	235	GLM 4 32B	820	±16	700	2.1%	2.6%	40 tps	1.6s	33K	$0.14	$0.14
23	222	Sky T1 32B Preview	821	±18	625	1.6%	7.8%	73 tps	0.6s	16K	$0.12	$0.18
24	214	OpenAI o3-mini-high	833	±13	2.9K	1.0%	2.4%	231 tps	10.5s	200K	$1.10	$4.40
25	177	Mistral Small 3.1 24B Instruct	839	±22	695	3.5%	7.5%	15 tps	2.4s	131K	$0.06	$0.18
26	179	Inception Mercury	847	±13	1.4K	1.0%	0.4%	257 tps	1.1s	32K	$0.25	$1.00
27	177	OpenAI o3-mini	851	±7	4.7K	1.8%	0.8%	143 tps	3.3s	200K	$1.10	$4.40
28	186	Grok 3 Mini	852	±14	2.5K	1.4%	1.2%	43 tps	0.5s	131K	$0.30	$0.50
29	175	OpenAI o3-mini-low	852	±8	4.4K	1.8%	0.7%	139 tps	1.5s	200K	$1.10	$4.40
30	186	GLM 4.6V Flash	858	±23	750	2.6%	3.7%	64 tps	2.1s	128K	$0.04	$0.40
31	209	Llama 3.3 Swallow 70B Instruct	865	±19	820	1.8%	1.4%	153 tps	1.3s	131K	$0.13	$0.39
32	170	Devstral Medium	865	±19	805	1.8%	1.5%	77 tps	0.6s	131K	$0.40	$2.00
33	194	Magistral Small 2506	870	±16	1K	2.8%	1.6%	156 tps	0.5s	40K	$0.37	$1.10
34	160	Llama 4 Scout	872	±11	4.4K	1.4%	0.6%	88 tps	5.1s	131K	$0.18	$0.46
35	157	Cogito v2.1 671B	876	±30	490	3.9%	0.8%	85 tps	0.5s	128K	$1.25	$1.25
36	201	Gemma 3 27B IT	879	±21	560	1.8%	2.0%	60 tps	0.8s	128K	$0.17	$0.29
37	139	GLM 4.6V	880	±33	885	2.2%	6.4%	21 tps	1.8s	128K	$0.38	$0.90
38	143	Seed 1.6 250615	888	±23	530	2.8%	3.1%	46 tps	2.2s	256K	$0.25	$2.00
39	161	Llama 4 Maverick	900	±11	5.1K	1.9%	1.2%	88 tps	2.4s	1M	$0.23	$0.83
40	148	DeepSeek-R1	904	±16	1.7K	2.8%	0.8%	133 tps	0.6s	64K	$0.91	$3.07
41	148	OpenAI o4-mini-high	915	±10	4.7K	1.5%	1.9%	117 tps	15.9s	200K	$1.10	$4.40
42	133	DeepSeek V3.2 Speciale	922	±25	780	6.6%	6.0%	43 tps	1.4s	131K	$0.84	$1.52
43	111	Grok 3 Fast	922	±12	530	0.9%	1.7%	52 tps	2.4s	131K	$5.00	$25.00
44	161	Mistral Small 3.1	924	±36	615	2.4%	7.4%	13 tps	2.6s	32K	$0.17	$0.28
45	106	DeepSeek V3.1 Terminus Thinking	927	±17	840	4.5%	5.9%	27 tps	1.8s	131K	$0.56	$1.68
46	170	Mistral Small 3.2 24B	929	±14	985	2.5%	2.8%	141 tps	0.7s	33K	$0.02	$0.08
47	170	Kimi K2 0711	932	±12	2.4K	1.7%	1.6%	29 tps	1.3s	131K	$0.72	$2.60
48	179	GLM 4.7 Flash	932	±26	690	2.1%	5.8%	61 tps	2.8s	128K	$0.07	$0.39
49	165	Qwen3 4B	940	±14	1.7K	5.2%	1.9%	94 tps	1.5s	128K	$0.01	$0.01
50	165	Pixtral Large	941	±18	940	3.6%	2.5%	57 tps	1.3s	128K	$1.50	$4.50
51	153	OpenAI o1	946	±11	3.6K	1.0%	4.2%	92 tps	5.5s	200K	$15.00	$60.00
52	143	Gemini 2.0 Flash Lite	948	±7	3.5K	1.7%	<0.1%	42 tps	0.5s	1M	$0.08	$0.30
53	86	Amazon Nova 2 Lite	948	±21	970	7.6%	1.0%	137 tps	0.6s	300K	$0.35	$2.95
54	157	GPT-5 Nano	955	±18	1.2K	4.1%	3.2%	113 tps	20.9s	400K	$0.05	$0.40
55	133	GPT-4.1 nano	958	±8	4K	1.4%	0.6%	175 tps	0.5s	1M	$0.10	$0.40
56	129	Command A	959	±8	6.2K	1.2%	2.2%	42 tps	0.8s	256K	$2.00	$7.33
57	71	DeepSeek V3.1	962	±20	750	3.2%	0.8%	197 tps	0.4s	164K	$0.55	$1.60
58	143	Gemini 2.0 Flash	965	±12	1.8K	1.3%	<0.1%	76 tps	0.5s	1M	$0.14	$0.56
59	148	OpenAI o3	968	±12	1.6K	1.6%	0.9%	85 tps	6.8s	128K	$7.33	$29.33
60	139	OpenAI o4-mini	971	±8	2.2K	2.6%	1.4%	97 tps	7.0s	128K	$1.10	$4.40
61	65	Mistral Large 3	974	±20	1.2K	5.5%	2.1%	51 tps	1.0s	256K	$0.50	$1.50
62	126	DeepSeek V3	975	±10	5.5K	0.5%	0.9%	69 tps	1.1s	64K	$0.59	$1.49
63	129	DeepSeek V3.1 Thinking	984	±13	1.4K	3.7%	7.1%	18 tps	1.8s	131K	$0.23	$0.75
64	126	Qwen3 30B A3B	986	±16	1.9K	3.4%	5.1%	163 tps	1.0s	41K	$0.06	$0.21
65	113	GLM 4.5	986	±15	1.5K	2.0%	3.7%	46 tps	1.4s	131K	$0.43	$1.63
66	161	Qwen3 8B	991	±11	1.4K	2.5%	2.4%	61 tps	1.4s	41K	$0.02	$0.07
67	71	Seed 1.8 251228	997	±13	2.4K	1.3%	3.7%	41 tps	2.1s	256K	$0.25	$2.00
68	86	Qwen3 235B A22B	998	±18	1.4K	3.2%	5.3%	71 tps	0.9s	41K	$0.23	$0.63
69	118	GPT-4.1 mini	999	±10	5.1K	1.4%	1.1%	67 tps	0.9s	1M	$0.34	$1.60
70	65	GLM 4.6	1001	±15	1.3K	4.4%	5.4%	39 tps	1.5s	200K	$0.42	$1.66
71	153	Qwen 2.5 32B Instruct	1004	±14	1.2K	1.7%	2.5%	48 tps	1.0s	131K	$0.21	$0.25
72	86	Claude Sonnet 4	1013	±7	10.4K	1.2%	1.8%	49 tps	1.3s	200K	$3.00	$15.00
73	119	ERNIE 4.5 300B A47B	1014	±11	4K	1.1%	4.7%	23 tps	2.3s	123K	$0.28	$1.10
74	121	QwQ 32B	1015	±7	4.6K	1.4%	5.4%	41 tps	2.1s	16K	$0.43	$0.56
75	124	Kimi K2 0905 Turbo	1017	±12	2.1K	2.3%	0.7%	373 tps	0.5s	262K	$1.70	$6.50
76	71	Qwen3.5 397B A17B	1021	±22	910	1.1%	4.3%	57 tps	1.4s	256K	$0.52	$3.00
77	129	Qwen3 Max Thinking	1022	±12	1.3K	1.1%	13.5%	32 tps	2.3s	256K	$1.20	$6.00
78	62	MiniMax M2	1027	±9	2.5K	5.2%	2.2%	39 tps	2.3s	205K	$0.21	$0.85
79	126	Qwen3 VL 235B A22B Thinking	1027	±13	935	4.1%	4.3%	47 tps	3.0s	127K	$0.47	$3.31
80	48	Claude Sonnet 4 (Thinking)	1028	±15	3.7K	2.9%	1.5%	52 tps	1.5s	200K	$3.00	$13.67
81	165	DeepSeek R1T2 Chimera	1031	±17	575	3.4%	3.0%	28 tps	1.8s	164K	$0.13	$0.45
82	81	OpenAI o3-pro	1037	±18	950	2.6%	5.2%	22 tps	70.8s	200K	$20.00	$80.00
83	133	DeepSeek-R1 0528	1038	±13	1.7K	2.0%	1.3%	93 tps	0.5s	64K	$1.60	$3.67
84	113	Gemini 2.5 Flash Lite Thinking	1041	±9	2.2K	1.8%	1.0%	118 tps	4.4s	1M	$0.03	$0.13
85	106	Grok 3	1044	±7	6K	1.1%	1.5%	53 tps	0.6s	1M	$3.67	$18.33
86	106	DeepSeek V3 0324	1045	±8	4.1K	1.0%	5.8%	12 tps	2.7s	164K	$0.38	$0.93
87	95	DeepSeek V3.2 Exp Thinking	1046	±18	735	4.5%	7.2%	26 tps	3.0s	131K	$0.28	$0.42
88	37	Kimi K2.5 Instant	1046	±16	620	2.4%	2.9%	32 tps	3.0s	262K	$0.50	$3.00
89	71	GPT-5 Mini	1047	±9	2.2K	2.7%	2.6%	66 tps	14.2s	400K	$0.25	$2.00
90	68	GLM 4.7	1047	±15	2.4K	1.2%	5.8%	40 tps	1.5s	200K	$0.77	$1.73
91	157	Qwen3 Next 80B A3B Thinking	1049	±9	2K	2.6%	0.6%	175 tps	1.3s	256K	$0.21	$2.26
92	56	MiniMax M2.1 Lightning	1050	±23	615	1.6%	1.7%	52 tps	2.1s	205K	$0.30	$2.40
93	95	Gemini 2.5 Flash Lite Thinking Preview 0925	1051	±15	1.5K	4.2%	1.5%	152 tps	3.0s	1M	$0.10	$0.40
94	133	Qwen3 14B	1053	±13	1.7K	2.9%	1.7%	109 tps	0.8s	41K	$0.04	$0.15
95	52	Qwen3.5 122B A17B	1053	±25	580	3.3%	1.5%	82 tps	1.4s	256K	$0.40	$3.20
96	65	DeepSeek V3.2 Exp Chat	1054	±14	1.2K	3.7%	2.6%	29 tps	1.5s	131K	$0.27	$0.39
97	71	Gemini 2.5 Flash Thinking	1055	±11	2.8K	2.3%	2.2%	88 tps	6.4s	1M	$0.30	$2.50
98	84	GPT-5 Mini Minimal	1057	±11	745	5.7%	1.2%	63 tps	1.4s	400K	$0.25	$2.00
99	86	Nemotron 3 Nano (Thinking)	1059	±18	825	1.8%	2.0%	200 tps	0.5s	256K	$0	$0
100	44	DeepSeek V3.1 Terminus Chat	1060	±13	1.4K	3.3%	3.4%	27 tps	1.5s	131K	$0.86	$1.80
101	121	Qwen3 32B Fast	1061	±9	3K	2.4%	11.6%	30 tps	3.1s	41K	$0.10	$0.25
102	95	Gemini 2.5 Flash	1061	±7	10K	1.0%	1.3%	2 tps	3.7s	1M	$0.30	$2.50
103	68	Grok 4	1062	±6	10.5K	1.3%	3.9%	29 tps	11.1s	256K	$3.00	$15.00
104	93	DeepSeek V3 0324 Turbo	1068	±7	4.2K	0.8%	6.3%	12 tps	2.4s	164K	$0.73	$1.79
105	86	DeepSeek V3.1 Chat	1069	±11	1.3K	3.0%	2.8%	21 tps	1.6s	131K	$0.38	$1.00
106	113	Kimi K2 Fast	1069	±7	8.5K	1.0%	0.8%	365 tps	0.5s	131K	$1.00	$3.00
107	60	MiniMax M2.1	1071	±11	2.6K	1.1%	2.1%	66 tps	2.6s	205K	$0.30	$1.20
108	95	Kimi K2 Thinking	1072	±30	880	8.8%	4.2%	61 tps	5.9s	262K	$0.24	$1.03
109	95	DeepSeek-R1 Turbo	1073	±16	780	3.7%	2.6%	29 tps	1.8s	64K	$2.85	$4.75
110	52	Claude Haiku 4.5	1078	±11	2.6K	3.7%	1.1%	100 tps	0.9s	200K	$1.00	$5.00
111	113	Mistral Medium	1079	±9	2.7K	1.8%	1.8%	48 tps	0.6s	33K	$1.48	$4.55
112	22	GLM 5	1080	±15	1.4K	1.4%	3.4%	36 tps	2.7s	200K	$0.72	$2.55
113	93	Qwen Max	1080	±7	5.4K	1.1%	1.5%	49 tps	1.5s	33K	$1.60	$6.40
114	148	Qwen3 30B A3B Thinking 2507	1081	±19	890	2.7%	0.5%	124 tps	1.2s	131K	$0.16	$1.70
115	56	DeepSeek V3.1 Turbo	1082	±16	1.8K	2.2%	0.9%	173 tps	1.3s	164K	$2.00	$3.75
116	52	GPT-5	1084	±7	5K	2.1%	3.1%	78 tps	23.1s	400K	$1.25	$9.67
117	101	gpt-oss-20b	1085	±12	2.1K	2.6%	0.5%	216 tps	0.5s	131K	$0.06	$0.26
118	124	Qwen3 235B A22B Thinking 2507	1091	±20	705	2.1%	2.5%	53 tps	1.6s	131K	$0.59	$5.70
119	79	Qwen3 Max Thinking Preview	1105	±14	1.9K	4.0%	3.1%	40 tps	2.1s	256K	$1.20	$6.00
120	52	Grok 4 Fast Non-Reasoning	1108	±12	1.8K	3.0%	1.5%	93 tps	0.6s	2M	$0.27	$0.67
121	101	Gemini 2.5 Flash Lite	1113	±6	4.4K	1.8%	1.3%	210 tps	0.7s	1M	$0.10	$0.40
122	71	Gemini 2.5 Flash Lite Preview 0925	1116	±10	2K	2.4%	1.2%	209 tps	0.7s	1M	$0.25	$0.35
123	79	MiniMax M2.5 Lightning	1119	±16	650	0.8%	1.5%	51 tps	2.0s	205K	$0.60	$2.40
124	111	LongCat Flash Chat	1121	±17	725	4.6%	0.8%	85 tps	0.9s	131K	$0.14	$0.68
125	40	DeepSeek V3.2	1125	±10	2.1K	1.6%	1.4%	83 tps	5.1s	131K	$0.43	$1.09
126	26	GPT-5 (High)	1131	±9	2.7K	3.2%	4.5%	81 tps	35.9s	400K	$1.25	$10.00
127	133	Kimi K2 0905	1145	±10	1.5K	2.0%	4.0%	30 tps	1.4s	262K	$0.63	$2.39
128	106	Claude Sonnet 3.5 v2	1147	±14	1K	2.0%	<0.1%	46 tps	1.4s	200K	$3.00	$15.00
129	37	Claude Sonnet 4.5	1148	±9	3.3K	2.7%	1.4%	41 tps	1.3s	200K	$1.80	$9.00
130	37	Qwen3 Omni 30B A3B Thinking	1150	±16	845	3.4%	3.7%	67 tps	1.2s	66K	$0.97	$1.79
131	60	Gemini 2.5 Flash Preview 0925	1151	±9	1.8K	3.3%	1.2%	5 tps	0.9s	1M	$0.13	$0.97
132	68	Qwen Plus (Aug'24)	1152	±9	4.8K	1.1%	1.4%	53 tps	1.3s	30K	$0.40	$1.20
133	48	Grok 4 Fast Reasoning	1154	±10	2.2K	3.0%	2.1%	102 tps	3.1s	2M	$0.30	$0.75
134	26	Claude Haiku 4.5 (Extended Thinking)	1154	±8	2.4K	2.8%	1.4%	115 tps	0.7s	200K	$1.00	$5.00
135	56	DeepSeek V3.2 Thinking	1158	±19	2.4K	2.3%	9.0%	30 tps	2.6s	131K	$0.28	$0.42
136	44	Grok 4.1 Fast Reasoning	1159	±11	4.3K	2.9%	1.5%	58 tps	7.3s	2M	$0.20	$0.50
137	44	Gemini 2.5 Pro	1161	±6	12.1K	1.4%	2.3%	45 tps	2.6s	1M	$1.25	$10.00
138	56	Gemini 3.1 Flash Lite Preview Thinking	1162	±19	730	2.0%	1.7%	75 tps	4.7s	1M	$0.25	$1.50
139	48	Step 3.5 Flash	1163	±23	640	0.8%	2.2%	109 tps	0.6s	256K	$0.05	$0.15
140	44	Kimi K2 Thinking Turbo	1171	±11	1.8K	4.2%	2.0%	75 tps	1.4s	262K	$1.15	$8.00
141	42	GPT-5.2 (Extra High)	1172	±13	3K	1.6%	13.2%	17 tps	20.5s	400K	$1.75	$14.00
142	33	Kimi K2.5	1175	±12	3.1K	1.6%	6.5%	33 tps	1.7s	262K	$0.34	$2.57
143	17	Claude Opus 4.5	1177	±15	1.9K	4.7%	1.5%	45 tps	1.5s	200K	$5.00	$25.00
144	29	Nova Experimental Chat 12-10	1192	±11	1.4K	0.7%	2.4%	84 tps	12.9s	98K	$0	$0
145	42	Qwen3 Max Instruct Preview	1192	±9	2.8K	3.0%	1.1%	31 tps	1.7s	256K	$1.43	$6.61
146	13	GPT-5.3 Instant	1225	±13	2.3K	1.3%	0.9%	63 tps	0.8s	400K	$1.75	$14.00
147	81	GPT-4o	1228	±11	2.9K	1.7%	1.0%	49 tps	2.4s	128K	$3.71	$12.57
148	62	GPT-5.1 Instant	1233	±12	2.6K	2.7%	1.3%	50 tps	1.9s	400K	$1.25	$10.00
149	32	Gemini 2.5 Pro High	1234	±6	4.6K	2.4%	1.5%	48 tps	2.3s	1M	$1.25	$10.00
150	14	Gemini 3 Flash Preview Thinking	1248	±10	3.7K	1.3%	1.6%	3 tps	6.2s	1M	$0.50	$3.00
151	26	Grok 4.1 Fast Non-Reasoning	1260	±16	2.5K	3.7%	0.9%	101 tps	0.5s	2M	$0.20	$0.50
152	10	Claude Sonnet 4.5 (Thinking)	1261	±7	5.5K	1.9%	1.9%	44 tps	1.1s	200K	$3.00	$15.00
153	40	Qwen3 235B A22B Instruct 2507	1261	±8	3.1K	1.4%	6.8%	13 tps	1.9s	262K	$0.13	$0.52
154	48	gpt-oss-120b	1269	±7	4.6K	1.4%	0.7%	213 tps	0.5s	131K	$0.11	$0.50
155	22	GPT-5 Chat	1269	±5	7.9K	1.6%	1.3%	95 tps	0.9s	400K	$1.25	$10.00
156	33	Qwen3 Next 80B A3B Instruct	1270	±10	2.3K	2.8%	0.6%	84 tps	1.1s	256K	$0.20	$1.42
157	29	Qwen3 VL 235B A22B Instruct	1273	±14	1.1K	2.3%	3.1%	75 tps	1.9s	129K	$0.37	$1.81
158	17	GPT-5.2 (High)	1275	±12	6.5K	1.4%	6.7%	18 tps	16.3s	400K	$1.75	$14.00
159	5	Claude Sonnet 4.6 (Thinking)	1280	±14	1.4K	2.2%	4.7%	57 tps	1.1s	200K	$3.00	$15.00
160	17	Gemini 3 Flash Preview	1281	±11	2K	1.2%	1.3%	138 tps	1.4s	1M	$0.50	$3.00
161	14	Gemini 3 Pro (Low)	1300	±8	4.1K	1.8%	2.4%	51 tps	3.5s	1M	$2.00	$12.00
162	7	Claude Opus 4.5 (Thinking)	1313	±9	6K	2.5%	1.8%	49 tps	1.4s	200K	$5.00	$25.00
163	16	GPT-5.2	1329	±9	3.2K	1.2%	4.1%	18 tps	2.7s	400K	$1.75	$14.00
164	10	Gemini 3 Pro	1343	±7	16.2K	1.4%	2.1%	50 tps	3.6s	1M	$2.00	$12.00
165	33	Qwen3 30B A3B Instruct 2507	1345	±6	3.4K	1.4%	1.2%	55 tps	1.3s	131K	$0.13	$0.72
166	8	GPT-5.1	1360	±9	2.6K	2.4%	2.3%	71 tps	1.4s	400K	$1.42	$11.33
167	10	GPT-5.2 Instant	1361	±11	4K	1.1%	1.7%	52 tps	2.0s	400K	$1.75	$14.00
168	4	Claude Sonnet 4.6	1364	±19	1.9K	1.3%	1.6%	47 tps	1.2s	200K	$3.00	$15.00
169	8	GPT-5.1 (High)	1368	±10	4.9K	2.2%	3.2%	76 tps	6.9s	400K	$1.25	$10.00
170	6	Gemini 3.1 Pro	1418	±11	4.9K	1.0%	3.5%	35 tps	4.1s	1M	$2.00	$12.00
171	2	Claude Opus 4.6	1469	±16	1.6K	2.4%	2.1%	48 tps	1.7s	200K	$5.00	$25.00
172	2	GPT-5.4	1493	±14	695	1.4%	2.6%	55 tps	0.8s	1M	$2.50	$15.00
173	1	Claude Opus 4.6 (Thinking)	1569	±10	1.5K	1.7%	2.5%	56 tps	1.6s	200K	$5.00	$25.00

Show Less