Leaderboard | Coding

Models

Choose model family

Claude by Anthropic

Mistral by Mistral AI

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

1635

GPT-5.4

1616

Claude Sonnet 4.6

1611

Claude Opus 4.6

1596

Claude Opus 4.6 (Thinking)

1540

Claude Sonnet 4.6 (Thinking)

1485

Claude Opus 4.5

1464

Gemini 3.1 Pro

1462

Claude Opus 4.5 (Thinking)

1425

Claude Haiku 4.5 (Extended Thinking)

1417

Claude Sonnet 4.5 (Thinking)

1404

Claude Sonnet 4.5

1393

GPT-5.2 Instant

1393

GPT-5.3 Codex (High)

1378

GPT-5.2

1370

GPT-5.1

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	GPT-5.4	1635	±13	4K	1.6%	2.6%	55 tps	0.8s	1M	$2.50	$15.00
2	1	Claude Sonnet 4.6	1616	±9	13.6K	1.3%	1.6%	47 tps	1.2s	200K	$3.00	$15.00
3	1	Claude Opus 4.6	1611	±7	18.4K	0.9%	2.1%	48 tps	1.7s	200K	$5.00	$25.00
4	4	Claude Opus 4.6 (Thinking)	1596	±10	12.8K	1.2%	2.5%	56 tps	1.6s	200K	$5.00	$25.00
5	5	Claude Sonnet 4.6 (Thinking)	1540	±8	11.3K	2.6%	4.7%	57 tps	1.1s	200K	$3.00	$15.00
6	7	Claude Opus 4.5	1485	±6	11.7K	1.8%	1.5%	45 tps	1.5s	200K	$5.00	$25.00
7	7	Gemini 3.1 Pro	1464	±9	15.6K	1.9%	3.5%	35 tps	4.1s	1M	$2.00	$12.00
8	6	Claude Opus 4.5 (Thinking)	1462	±5	43.2K	1.6%	1.8%	49 tps	1.4s	200K	$5.00	$25.00
9	12	Claude Haiku 4.5 (Extended Thinking)	1425	±7	10K	3.7%	1.4%	115 tps	0.7s	200K	$1.00	$5.00
10	10	Claude Sonnet 4.5 (Thinking)	1417	±5	37.7K	2.9%	1.9%	44 tps	1.1s	200K	$3.00	$15.00
11	17	Claude Sonnet 4.5	1404	±6	12.9K	5.0%	1.4%	41 tps	1.3s	200K	$1.80	$9.00
12	10	GPT-5.2 Instant	1393	±9	12.1K	3.2%	1.7%	52 tps	2.0s	400K	$1.75	$14.00
13	9	GPT-5.3 Codex (High)	1393	±14	2.8K	0.9%	2.0%	61 tps	17.8s	400K	$1.75	$14.00
14	13	GPT-5.2	1378	±8	8.5K	2.9%	4.1%	18 tps	2.7s	400K	$1.75	$14.00
15	15	GPT-5.1	1370	±7	9.1K	3.6%	2.3%	71 tps	1.4s	400K	$1.42	$11.33
16	13	Gemini 3 Pro	1362	±9	34.5K	2.5%	2.1%	50 tps	3.6s	1M	$2.00	$12.00
17	17	GPT-5.2 (High)	1344	±9	16.4K	2.8%	6.7%	18 tps	16.3s	400K	$1.75	$14.00
18	19	Claude Haiku 4.5	1344	±7	10.5K	4.5%	1.1%	100 tps	0.9s	200K	$1.00	$5.00
19	15	GLM 5	1329	±14	3.9K	3.1%	3.4%	36 tps	2.7s	200K	$0.72	$2.55
20	19	GPT-5.3 Instant	1321	±15	3.4K	2.2%	0.9%	63 tps	0.8s	400K	$1.75	$14.00
21	19	Gemini 3 Pro (Low)	1319	±8	8.9K	4.2%	2.4%	51 tps	3.5s	1M	$2.00	$12.00
22	19	Kimi K2.5	1307	±15	6.4K	3.2%	6.5%	33 tps	1.7s	262K	$0.34	$2.57
23	27	Claude Sonnet 4 (Thinking)	1304	±5	19.2K	2.6%	1.5%	52 tps	1.5s	200K	$3.00	$13.67
24	19	GPT-5.3 Codex (Medium)	1299	±15	890	2.2%	2.3%	62 tps	10.3s	400K	$1.75	$14.00
25	19	Gemini 3 Flash Preview Thinking	1289	±9	14.1K	3.6%	1.6%	3 tps	6.2s	1M	$0.50	$3.00
26	19	GPT-5.1 (High)	1289	±10	9.9K	4.1%	3.2%	76 tps	6.9s	400K	$1.25	$10.00
27	27	GPT-5 Codex (High)	1282	±5	11K	3.5%	3.2%	122 tps	7.1s	400K	$1.25	$10.00
28	36	Qwen3.5 122B A17B	1282	±18	1.3K	2.7%	1.5%	82 tps	1.4s	256K	$0.40	$3.20
29	31	GPT-5 Chat	1272	±4	20.8K	4.7%	1.3%	95 tps	0.9s	400K	$1.25	$10.00
30	31	GPT-5.1 Codex (High)	1271	±8	14.1K	3.4%	3.2%	96 tps	3.9s	400K	$1.25	$10.00
31	43	Claude Sonnet 4	1270	±6	23.4K	3.2%	1.8%	49 tps	1.3s	200K	$3.00	$15.00
32	36	GPT-5.2 Codex (Medium)	1264	±16	2.1K	2.6%	5.7%	37 tps	6.3s	400K	$1.75	$14.00
33	27	GPT-5.2 Codex (High)	1255	±14	2.6K	2.6%	8.8%	41 tps	12.9s	400K	$1.75	$14.00
34	43	GPT-5.1 Codex Max	1254	±9	4.3K	4.0%	3.0%	118 tps	4.1s	400K	$1.25	$10.00
35	43	Gemini 3 Flash Preview	1245	±11	5.5K	3.7%	1.3%	138 tps	1.4s	1M	$0.50	$3.00
36	31	Qwen3 Next 80B A3B Instruct	1241	±11	3.5K	8.9%	0.6%	84 tps	1.1s	256K	$0.20	$1.42
37	77	Grok 4.20 Multi Agent Beta	1240	±23	685	3.5%	1.2%	56 tps	8.8s	2M	$2.00	$6.00
38	49	Grok 4 Fast Non-Reasoning	1232	±7	3.9K	9.8%	1.5%	93 tps	0.6s	2M	$0.27	$0.67
39	74	Qwen3.5 397B A17B	1231	±20	1.7K	2.8%	4.3%	57 tps	1.4s	256K	$0.52	$3.00
40	36	Qwen3.5 27B	1230	±17	690	4.2%	3.7%	55 tps	2.6s	256K	$0.30	$2.40
41	31	Grok 4.1 Fast Non-Reasoning	1226	±13	5.8K	6.3%	0.9%	101 tps	0.5s	2M	$0.20	$0.50
42	43	Qwen3 Max Instruct Preview	1226	±9	4.7K	7.7%	1.1%	31 tps	1.7s	256K	$1.43	$6.61
43	36	GPT-5 Codex (Medium)	1224	±10	6.2K	3.9%	4.1%	122 tps	5.2s	400K	$1.25	$10.00
44	49	Qwen3 30B A3B Instruct 2507	1220	±7	5.7K	7.3%	1.2%	55 tps	1.3s	131K	$0.13	$0.72
45	36	GPT-5.2 (Extra High)	1218	±13	5.4K	3.6%	13.2%	17 tps	20.5s	400K	$1.75	$14.00
46	60	GPT-5.1 Instant	1211	±8	5.8K	4.2%	1.3%	50 tps	1.9s	400K	$1.25	$10.00
47	49	GPT-5	1209	±6	12.4K	6.7%	3.1%	78 tps	23.1s	400K	$1.25	$9.67
48	49	MiniMax M2.1	1204	±10	6.9K	5.1%	2.1%	66 tps	2.6s	205K	$0.30	$1.20
49	60	GPT-5.1 Codex (Medium)	1202	±20	2.5K	2.9%	4.6%	71 tps	3.7s	400K	$1.25	$10.00
50	36	Qwen3 VL 235B A22B Instruct	1197	±9	2.9K	7.7%	3.1%	75 tps	1.9s	129K	$0.37	$1.81
51	27	GPT-5 (High)	1194	±8	8.9K	4.0%	4.5%	81 tps	35.9s	400K	$1.25	$10.00
52	60	Grok 4 Fast Reasoning	1194	±8	7.7K	6.5%	2.1%	102 tps	3.1s	2M	$0.30	$0.75
53	36	Kimi K2.5 Instant	1191	±14	1.4K	3.4%	2.9%	32 tps	3.0s	262K	$0.50	$3.00
54	69	GPT-5 Codex (Low)	1188	±10	3.3K	4.2%	2.7%	112 tps	3.5s	400K	$1.25	$10.00
55	43	MiniMax M2.1 Lightning	1187	±31	655	3.0%	1.7%	52 tps	2.1s	205K	$0.30	$2.40
56	60	Claude Sonnet 3.5 v2	1186	±8	4.9K	3.4%	<0.1%	46 tps	1.4s	200K	$3.00	$15.00
57	60	Qwen3 235B A22B Instruct 2507	1181	±7	6.8K	7.8%	6.8%	13 tps	1.9s	262K	$0.13	$0.52
58	49	GLM 4.6	1179	±10	4.4K	8.3%	5.4%	39 tps	1.5s	200K	$0.42	$1.66
59	90	Grok 3 Fast	1179	±22	1.1K	1.7%	1.7%	52 tps	2.4s	131K	$5.00	$25.00
60	49	Kimi K2 Thinking Turbo	1177	±13	5.3K	4.5%	2.0%	75 tps	1.4s	262K	$1.15	$8.00
61	49	DeepSeek V3.2	1173	±13	3K	5.9%	1.4%	83 tps	5.1s	131K	$0.43	$1.09
62	69	DeepSeek V3.1 Terminus Chat	1171	±9	2.6K	10.5%	3.4%	27 tps	1.5s	131K	$0.86	$1.80
63	31	MiniMax M2.5 Lightning	1171	±27	1.1K	2.3%	1.5%	51 tps	2.0s	205K	$0.60	$2.40
64	60	Gemini 2.5 Pro	1167	±5	23K	5.7%	2.3%	45 tps	2.6s	1M	$1.25	$10.00
65	49	MiniMax M2	1166	±8	5.4K	7.5%	2.2%	39 tps	2.3s	205K	$0.21	$0.85
66	43	Gemini 2.5 Pro High	1164	±6	10.4K	7.1%	1.5%	48 tps	2.3s	1M	$1.25	$10.00
67	60	Grok 4.20 Beta Reasoning	1157	±20	930	4.1%	1.1%	77 tps	4.5s	2M	$2.00	$5.50
68	60	DeepSeek V3.2 Thinking	1153	±9	6.7K	4.6%	9.0%	30 tps	2.6s	131K	$0.28	$0.42
69	69	gpt-oss-120b	1152	±7	8.5K	8.0%	0.7%	213 tps	0.5s	131K	$0.11	$0.50
70	60	Grok 4.1 Fast Reasoning	1151	±6	12.8K	5.4%	1.5%	58 tps	7.3s	2M	$0.20	$0.50
71	74	Qwen Plus (Aug'24)	1134	±7	8.3K	4.9%	1.4%	53 tps	1.3s	30K	$0.40	$1.20
72	69	GLM 4.7	1134	±9	5.8K	5.5%	5.8%	40 tps	1.5s	200K	$0.77	$1.73
73	77	GPT-5 Mini	1133	±6	6.5K	6.0%	2.6%	66 tps	14.2s	400K	$0.25	$2.00
74	85	GPT-5.2 Codex (Low)	1131	±27	1K	3.3%	4.5%	41 tps	5.0s	400K	$1.75	$14.00
75	77	Grok 4	1129	±5	21.3K	5.4%	3.9%	29 tps	11.1s	256K	$3.00	$15.00
76	77	GPT-4.1	1127	±5	16.2K	1.8%	3.7%	112 tps	1.3s	1M	$2.00	$8.00
77	85	Gemini 2.5 Flash Thinking	1123	±7	10.7K	3.7%	2.2%	88 tps	6.4s	1M	$0.30	$2.50
78	77	Qwen3 Max Thinking Preview	1122	±14	3K	7.8%	3.1%	40 tps	2.1s	256K	$1.20	$6.00
79	98	Grok 3	1120	±8	9.2K	4.8%	1.5%	53 tps	0.6s	1M	$3.67	$18.33
80	90	Qwen Max	1119	±6	9K	4.7%	1.5%	49 tps	1.5s	33K	$1.60	$6.40
81	77	Gemini 2.5 Flash Lite Preview 0925	1117	±8	4.3K	7.4%	1.2%	209 tps	0.7s	1M	$0.25	$0.35
82	105	Qwen3 Max Thinking	1115	±23	945	2.1%	13.5%	32 tps	2.3s	256K	$1.20	$6.00
83	74	Gemini 2.5 Flash Preview 0925	1115	±11	4.1K	6.8%	1.2%	5 tps	0.9s	1M	$0.13	$0.97
84	98	Gemini 2.5 Flash	1115	±5	17.3K	3.5%	1.3%	2 tps	3.7s	1M	$0.30	$2.50
85	90	DeepSeek V3 0324	1113	±7	7.7K	5.1%	5.8%	12 tps	2.7s	164K	$0.38	$0.93
86	98	DeepSeek V3 0324 Turbo	1111	±5	6.5K	6.3%	6.3%	12 tps	2.4s	164K	$0.73	$1.79
87	85	DeepSeek V3.1 Chat	1108	±12	2.4K	9.3%	2.8%	21 tps	1.6s	131K	$0.38	$1.00
88	119	GPT-5.1 Codex Mini (Medium)	1104	±15	1.6K	4.6%	4.6%	69 tps	4.1s	400K	$0.25	$2.00
89	49	Nova Experimental Chat 12-10	1101	±15	1.4K	5.3%	2.4%	84 tps	12.9s	98K	$0	$0
90	69	Qwen3.5 35B A3B	1095	±30	675	3.6%	2.1%	116 tps	2.1s	256K	$0.63	$1.13
91	85	Qwen3 Omni 30B A3B Thinking	1091	±12	1.7K	6.5%	3.7%	67 tps	1.2s	66K	$0.97	$1.79
92	90	GPT-4o	1090	±8	6.5K	3.8%	1.0%	49 tps	2.4s	128K	$3.71	$12.57
93	105	GPT-4.1 nano	1086	±7	9.8K	4.1%	0.6%	175 tps	0.5s	1M	$0.10	$0.40
94	90	Qwen3 Coder 480B A35B Instruct	1085	±14	1.8K	4.0%	3.3%	61 tps	2.0s	262K	$0.71	$1.34
95	128	Gemini 3.1 Flash Lite Preview Thinking	1085	±31	1.1K	4.0%	1.7%	75 tps	4.7s	1M	$0.25	$1.50
96	98	OpenAI o3-pro	1085	±15	2.8K	3.8%	5.2%	22 tps	70.8s	200K	$20.00	$80.00
97	90	Gemini 2.5 Flash Lite	1083	±7	11.8K	6.9%	1.3%	210 tps	0.7s	1M	$0.10	$0.40
98	105	Qwen3 Omni 30B A3B Instruct	1083	±21	600	4.0%	3.9%	65 tps	1.2s	66K	$0.35	$0.97
99	85	GPT-5 Mini Minimal	1082	±12	2.3K	9.3%	1.2%	63 tps	1.4s	400K	$0.25	$2.00
100	98	DeepSeek V3.1	1078	±15	1.8K	4.8%	0.8%	197 tps	0.4s	164K	$0.55	$1.60
101	77	DeepSeek V3.1 Turbo	1068	±16	2.8K	6.1%	0.9%	173 tps	1.3s	164K	$2.00	$3.75
102	119	GPT-5.1 Codex Mini (High)	1065	±19	1.9K	3.6%	5.9%	70 tps	4.6s	400K	$0.25	$2.00
103	77	Mistral Large 3	1065	±10	3.2K	5.6%	2.1%	51 tps	1.0s	256K	$0.50	$1.50
104	90	DeepSeek V3.2 Exp Chat	1065	±14	2.2K	9.0%	2.6%	29 tps	1.5s	131K	$0.27	$0.39
105	119	Gemini 2.5 Flash Lite Thinking	1064	±8	7.4K	6.8%	1.0%	118 tps	4.4s	1M	$0.03	$0.13
106	112	Kimi K2 Fast	1061	±5	16.4K	9.2%	0.8%	365 tps	0.5s	131K	$1.00	$3.00
107	148	Qwen3 VL 235B A22B Thinking	1055	±12	2.5K	9.4%	4.3%	47 tps	3.0s	127K	$0.47	$3.31
108	105	Mistral Medium	1053	±7	5.5K	4.6%	1.8%	48 tps	0.6s	33K	$1.48	$4.55
109	128	Cogito v2.1 671B	1053	±21	920	5.2%	0.8%	85 tps	0.5s	128K	$1.25	$1.25
110	98	Qwen3 235B A22B	1050	±9	3.5K	8.8%	5.3%	71 tps	0.9s	41K	$0.23	$0.63
111	135	Gemini 2.0 Flash Lite	1050	±8	9.1K	3.4%	<0.1%	42 tps	0.5s	1M	$0.08	$0.30
112	112	Kimi K2 0905 Turbo	1050	±13	3.2K	13.0%	0.7%	373 tps	0.5s	262K	$1.70	$6.50
113	112	Kimi K2 0905	1047	±13	1.8K	8.5%	4.0%	30 tps	1.4s	262K	$0.63	$2.39
114	105	GPT-4.1 mini	1046	±8	8.7K	4.0%	1.1%	67 tps	0.9s	1M	$0.34	$1.60
115	98	DeepSeek V3.2 Exp Thinking	1046	±17	1.7K	6.2%	7.2%	26 tps	3.0s	131K	$0.28	$0.42
116	128	Qwen3 32B	1046	±34	535	7.8%	3.9%	30 tps	3.1s	41K	$0.12	$0.42
117	128	ERNIE 4.5 300B A47B	1044	±7	8.7K	3.6%	4.7%	23 tps	2.3s	123K	$0.28	$1.10
118	135	Qwen3 Next 80B A3B Thinking	1043	±15	2.7K	11.3%	0.6%	175 tps	1.3s	256K	$0.21	$2.26
119	119	Qwen3 32B Fast	1043	±10	6.6K	6.4%	11.6%	30 tps	3.1s	41K	$0.10	$0.25
120	135	Qwen3 VL 30B A3B Instruct	1042	±21	860	7.0%	1.8%	80 tps	2.6s	129K	$0.18	$0.67
121	112	GLM 4.5	1038	±9	3.2K	8.8%	3.7%	46 tps	1.4s	131K	$0.43	$1.63
122	135	Gemini 2.5 Flash Lite Thinking Preview 0925	1035	±10	4.6K	7.3%	1.5%	152 tps	3.0s	1M	$0.10	$0.40
123	135	Gemini 3.1 Flash Lite Preview	1034	±30	775	4.3%	1.0%	8 tps	1.2s	1M	$0.25	$1.50
124	144	Gemini 2.0 Flash	1034	±7	7.7K	3.6%	<0.1%	76 tps	0.5s	1M	$0.14	$0.56
125	135	DeepSeek V3	1032	±6	8.4K	2.7%	0.9%	69 tps	1.1s	64K	$0.59	$1.49
126	119	LongCat Flash Chat	1032	±12	2.2K	5.9%	0.8%	85 tps	0.9s	131K	$0.14	$0.68
127	135	QwQ 32B	1030	±9	6.4K	7.9%	5.4%	41 tps	2.1s	16K	$0.43	$0.56
128	128	OpenAI o4-mini	1027	±11	4.1K	8.7%	1.4%	97 tps	7.0s	128K	$1.10	$4.40
129	135	DeepSeek V3.2 Speciale	1026	±18	1.6K	6.9%	6.0%	43 tps	1.4s	131K	$0.84	$1.52
130	148	Qwen3 235B A22B Thinking 2507	1024	±22	1.9K	5.1%	2.5%	53 tps	1.6s	131K	$0.59	$5.70
131	144	Command A	1021	±7	11.9K	4.1%	2.2%	42 tps	0.8s	256K	$2.00	$7.33
132	105	DeepSeek V3 (Turbo)	1020	±25	865	6.0%	1.5%	32 tps	1.5s	64K	$0.40	$1.30
133	119	OpenAI o1	1019	±13	4.3K	4.2%	4.2%	92 tps	5.5s	200K	$15.00	$60.00
134	159	Grok Code Fast 1	1018	±10	2K	5.6%	5.9%	294 tps	0.5s	256K	$0.20	$1.50
135	112	GPT-5 (Low)	1018	±28	480	5.0%	1.8%	75 tps	8.2s	400K	$1.25	$10.00
136	148	Nemotron 3 Nano (Thinking)	1018	±17	1.4K	6.3%	2.0%	200 tps	0.5s	256K	$0	$0
137	119	DeepSeek V3.1 Terminus Thinking	1016	±15	2.1K	10.7%	5.9%	27 tps	1.8s	131K	$0.56	$1.68
138	128	Kimi K2 Thinking	1013	±13	2.5K	5.4%	4.2%	61 tps	5.9s	262K	$0.24	$1.03
139	105	Seed 1.8 251228	1010	±19	2.1K	3.0%	3.7%	41 tps	2.1s	256K	$0.25	$2.00
140	148	DeepSeek-R1 Turbo	1005	±15	1.6K	6.3%	2.6%	29 tps	1.8s	64K	$2.85	$4.75
141	159	GPT-5 Nano	1001	±12	3.6K	8.3%	3.2%	113 tps	20.9s	400K	$0.05	$0.40
142	167	Llama 3.1 8B Turbo	999	±16	1.6K	1.5%	2.1%	650 tps	0.5s	128K	$0.13	$0.14
143	128	GLM 4.5 AirX	999	±39	635	8.6%	3.3%	75 tps	1.2s	131K	$1.10	$4.50
144	144	OpenAI o3	991	±13	4.7K	3.7%	0.9%	85 tps	6.8s	128K	$7.33	$29.33
145	167	Mistral Small 3.2 24B	990	±11	4.4K	4.7%	2.8%	141 tps	0.7s	33K	$0.02	$0.08
146	167	Pixtral Large	988	±20	2.3K	3.6%	2.5%	57 tps	1.3s	128K	$1.50	$4.50
147	148	Seed 1.6 250615	988	±22	1.2K	6.0%	3.1%	46 tps	2.2s	256K	$0.25	$2.00
148	148	Qwen3 30B A3B	987	±10	4.5K	8.3%	5.1%	163 tps	1.0s	41K	$0.06	$0.21
149	112	gpt-oss-20b	983	±10	4.1K	10.1%	0.5%	216 tps	0.5s	131K	$0.06	$0.26
150	148	Qwen3 Coder Plus	981	±33	500	3.8%	5.1%	56 tps	2.3s	128K	$1.80	$9.80
151	90	Step 3.5 Flash	981	±44	510	3.8%	2.2%	109 tps	0.6s	256K	$0.05	$0.15
152	167	Devstral Medium	978	±17	3.4K	5.0%	1.5%	77 tps	0.6s	131K	$0.40	$2.00
153	167	Qwen 2.5 32B Instruct	976	±11	2.9K	6.2%	2.5%	48 tps	1.0s	131K	$0.21	$0.25
154	167	DeepSeek V3.1 Thinking	974	±11	3.7K	11.1%	7.1%	18 tps	1.8s	131K	$0.23	$0.75
155	167	Qwen3 VL 30B A3B Thinking	973	±17	1.5K	9.3%	4.5%	84 tps	2.9s	127K	$0.20	$1.47
156	148	OpenAI o3-mini-high	972	±8	3.9K	5.1%	2.4%	231 tps	10.5s	200K	$1.10	$4.40
157	159	GLM 4.6V	972	±18	2.3K	5.8%	6.4%	21 tps	1.8s	128K	$0.38	$0.90
158	159	Mistral Small 3.1 24B Instruct	970	±15	2.8K	4.2%	7.5%	15 tps	2.4s	131K	$0.06	$0.18
159	167	Qwen 2.5 72B	969	±22	1.3K	4.0%	1.2%	96 tps	1.2s	131K	$0.14	$0.26
160	167	Llama 4 Scout	958	±7	9K	4.2%	0.6%	88 tps	5.1s	131K	$0.18	$0.46
161	167	Llama 4 Maverick	958	±5	11K	4.1%	1.2%	88 tps	2.4s	1M	$0.23	$0.83
162	179	Qwen3 30B A3B Thinking 2507	958	±12	2.3K	5.2%	0.5%	124 tps	1.2s	131K	$0.16	$1.70
163	148	Qwen 2.5 VL 32B Instruct	957	±24	690	3.5%	6.3%	43 tps	3.2s	128K	$0.35	$0.62
164	179	Switchpoint Router	955	±10	2.5K	3.4%	1.7%	71 tps	4.9s	131K	$0.85	$3.40
165	159	DeepSeek-R1 0528	954	±11	4.2K	3.7%	1.3%	93 tps	0.5s	64K	$1.60	$3.67
166	179	DeepSeek-R1	953	±9	5.4K	4.2%	0.8%	133 tps	0.6s	64K	$0.91	$3.07
167	189	Llama 3.3 Swallow 70B Instruct	949	±12	3.4K	5.4%	1.4%	153 tps	1.3s	131K	$0.13	$0.39
168	189	Open Mistral Nemo	948	±29	1.6K	4.6%	1.5%	171 tps	0.5s	131K	$0.15	$0.15
169	189	Jamba 1.6 Large	945	±8	3K	2.6%	2.0%	59 tps	1.2s	256K	$1.33	$5.33
170	135	Amazon Nova 2 Lite	945	±18	2K	7.3%	1.0%	137 tps	0.6s	300K	$0.35	$2.95
171	148	OpenAI o4-mini-high	940	±11	5.9K	8.3%	1.9%	117 tps	15.9s	200K	$1.10	$4.40
172	148	OpenAI o3-mini	939	±9	6.4K	8.1%	0.8%	143 tps	3.3s	200K	$1.10	$4.40
173	201	Llama 3 8B	939	±11	3.1K	3.4%	6.0%	85 tps	0.7s	8K	$0.12	$0.16
174	179	Ministral 14B 3.0	937	±19	760	8.4%	2.0%	119 tps	0.5s	128K	$0.20	$0.20
175	201	Moonshot V1 Auto	937	±23	900	3.7%	1.2%	54 tps	1.5s	8K	$2.00	$5.00
176	201	Magistral Small 2506	937	±12	3.5K	2.8%	1.6%	156 tps	0.5s	40K	$0.37	$1.10
177	189	Mistral Small 3.1	936	±12	2.4K	3.8%	7.4%	13 tps	2.6s	32K	$0.17	$0.28
178	159	Kimi K2 0711	936	±10	3.3K	5.7%	1.6%	29 tps	1.3s	131K	$0.72	$2.60
179	167	Qwen3 14B	936	±10	4.2K	9.1%	1.7%	109 tps	0.8s	41K	$0.04	$0.15
180	189	Devstral Small	934	±32	1.3K	5.0%	2.4%	180 tps	0.6s	131K	$0.10	$0.30
181	189	Grok 3 Mini	934	±9	4.6K	7.5%	1.2%	43 tps	0.5s	131K	$0.30	$0.50
182	179	Qwen3 8B	929	±12	3.4K	9.0%	2.4%	61 tps	1.4s	41K	$0.02	$0.07
183	179	Grok 3 Mini Fast	928	±9	4.8K	7.5%	1.6%	44 tps	0.5s	131K	$0.60	$4.00
184	179	DeepSeek Prover v2	926	±17	1.1K	3.2%	5.2%	14 tps	1.3s	164K	$0.40	$1.56
185	210	Magistral Medium 2509	923	±17	2.1K	9.6%	4.0%	58 tps	0.9s	131K	$2.00	$5.00
186	159	OpenAI o3-mini-low	920	±9	5.5K	8.9%	0.7%	139 tps	1.5s	200K	$1.10	$4.40
187	179	ERNIE 4.5 VL 424B A47B	918	±19	545	5.2%	4.9%	36 tps	3.5s	123K	$0.42	$1.25
188	210	Qwen 2.5 7B Turbo	918	±38	565	5.8%	0.5%	125 tps	0.4s	131K	$0.30	$0.30
189	179	NVIDIA Llama 3.3 Nemotron Super 49B v1.5	917	±33	820	7.9%	2.0%	50 tps	0.6s	131K	$0.09	$0.33
190	201	GPT-3.5 Turbo	916	±15	1.1K	2.2%	1.3%	74 tps	0.9s	16K	$0.75	$1.75
191	189	Inception Mercury Coder Small Beta	914	±34	570	2.6%	1.7%	270 tps	1.4s	32K	$0.25	$1.00
192	189	Codestral	911	±29	725	5.8%	5.2%	151 tps	0.9s	262K	$0.15	$0.45
193	210	Inception Mercury	911	±6	6.6K	3.2%	0.4%	257 tps	1.1s	32K	$0.25	$1.00
194	179	ERNIE 4.5 21B A3B	910	±24	510	7.3%	2.3%	78 tps	1.5s	120K	$0.05	$0.19
195	201	Amazon Nova Pro 1.0	908	±9	5.2K	3.6%	0.9%	96 tps	0.7s	300K	$0.80	$1.70
196	210	Mistral Small 3 24B Instruct	907	±12	1.7K	3.4%	2.6%	77 tps	0.6s	33K	$0.07	$0.14
197	210	Krutrim Spectre V2	904	±16	1.1K	0.9%	<0.1%	33 tps	3.1s	4K	$0.19	$0.19
198	201	Llama 3.2 11B Instruct	902	±14	2K	3.8%	1.5%	152 tps	0.5s	8K	$0.16	$0.16
199	210	Moonshot V1 128k	899	±23	1.1K	4.4%	1.4%	54 tps	1.5s	131K	$2.00	$5.00
200	210	Mistral Small 24B Instruct	894	±13	1.5K	4.2%	1.5%	84 tps	0.4s	33K	$0.80	$0.80
201	201	GPT-4o mini	893	±16	2.3K	5.4%	2.1%	71 tps	1.7s	128K	$0.15	$0.60
202	201	Mistral Small 3.2 24B Instruct	891	±24	805	8.5%	1.9%	113 tps	1.1s	131K	$0.02	$0.08
203	210	GLM 4 32B	888	±15	2.6K	4.0%	2.6%	40 tps	1.6s	33K	$0.14	$0.14
204	210	Hermes 2 Pro Llama 3 8B	888	±12	1.7K	2.2%	<0.1%	76 tps	1.0s	131K	$0.08	$0.09
205	210	Gemma 3 12B	887	±14	2.5K	4.8%	4.2%	73 tps	0.8s	131K	$0.05	$0.12
206	210	Mixtral 8x22B	885	±32	1.2K	4.3%	1.2%	140 tps	0.6s	64K	$2.00	$6.00
207	252	Hermes 4 405B FP8	883	±20	530	8.6%	3.5%	31 tps	0.9s	131K	$0.52	$1.73
208	210	Qwen 2.5 14B Instruct	881	±19	2.2K	5.2%	2.4%	40 tps	1.6s	1M	$0.40	$1.61
209	210	DeepSeek R1T2 Chimera	878	±11	1.8K	5.9%	3.0%	28 tps	1.8s	164K	$0.13	$0.45
210	210	Mistral Nemo	878	±23	890	2.7%	<0.1%	112 tps	0.4s	131K	$0.07	$0.13
211	210	Gemma 3 27B	877	±37	1K	6.8%	1.8%	35 tps	1.1s	66K	$0.06	$0.10
212	189	Llama 3.3 70B	876	±21	1.4K	8.4%	0.3%	500 tps	0.5s	8K	$0.48	$0.66
213	234	Gemma 3 27B IT	875	±11	2.3K	4.1%	2.0%	60 tps	0.8s	128K	$0.17	$0.29
214	240	Sky T1 32B Preview	869	±17	2.1K	3.6%	7.8%	73 tps	0.6s	16K	$0.12	$0.18
215	234	GPT-3.5 Turbo 16k	869	±11	2.7K	3.6%	<0.1%	22 tps	0.6s	16K	$3.00	$4.00
216	210	Mixtral 8x7B	868	±16	1.3K	4.9%	2.2%	142 tps	0.6s	33K	$0.23	$0.23
217	189	Jamba 1.7 Large	868	±28	810	8.0%	1.3%	58 tps	1.0s	256K	$1.33	$5.33
218	210	Mixtral 8x7B Instruct	867	±17	1.3K	3.8%	0.2%	79 tps	0.7s	33K	$0.23	$0.31
219	189	Seed 1.6 Flash 250715	864	±23	960	6.3%	2.5%	108 tps	1.6s	256K	$0.07	$0.30
220	234	Jamba 1.5 Large	862	±14	2.6K	3.4%	1.7%	48 tps	0.9s	256K	$1.50	$6.00
221	234	Command R 7B	861	±14	3.1K	4.4%	1.1%	76 tps	0.4s	128K	$0.04	$0.15
222	201	GLM 4.6V Flash	860	±23	1.9K	7.9%	3.7%	64 tps	2.1s	128K	$0.04	$0.40
223	210	Moonshot V1 8k	859	±18	890	4.8%	1.0%	55 tps	1.5s	8K	$0.20	$2.00
224	240	LFM2 8B A1B	858	±18	550	12.0%	<0.1%	142 tps	0.3s	33K	$0.01	$0.02
225	240	Qwen 2.5 7B	858	±15	2K	5.2%	3.7%	40 tps	1.9s	131K	$0.08	$0.27
226	210	Qwen3 4B	858	±13	3.7K	10.7%	1.9%	94 tps	1.5s	128K	$0.01	$0.01
227	210	Solar Mini 250422	856	±17	1.2K	5.7%	1.8%	90 tps	1.7s	33K	$0.15	$0.15
228	240	Krutrim 2	851	±14	2.1K	0.7%	12.5%	33 tps	2.1s	128K	$1.00	$1.00
229	189	Rnj-1 Instruct	846	±27	565	7.4%	0.6%	103 tps	0.3s	33K	$0.15	$0.15
230	240	Moonshot V1 32k	845	±23	905	3.2%	1.4%	53 tps	1.4s	33K	$1.00	$3.00
231	240	Mixtral-8x7B Instruct v0.1	840	±19	1.2K	4.0%	1.3%	54 tps	0.4s	33K	$0.60	$0.60
232	240	Gemma 2 27B	839	±15	1.5K	3.9%	1.4%	44 tps	1.4s	8K	$0.80	$0.80
233	234	Llama 3.3 70B Instruct Turbo	836	±16	1.1K	6.1%	2.0%	78 tps	1.0s	131K	$0.88	$0.88
234	210	Ministral 3B 2512	836	±60	505	7.3%	2.8%	339 tps	0.6s	131K	$0.10	$0.10
235	240	C4AI Aya Expanse 32B	833	±9	3.5K	3.1%	1.5%	43 tps	0.5s	128K	$0.50	$1.50
236	252	Phi 4	829	±16	1.6K	3.3%	5.1%	28 tps	1.3s	128K	$0.10	$0.32
237	252	WizardLM-2 8x22B	827	±15	1.6K	1.8%	11.6%	11 tps	2.5s	66K	$0.77	$0.77
238	252	Magistral Small 2509	827	±27	1.5K	7.3%	2.7%	116 tps	0.6s	131K	$0.50	$1.50
239	210	Gemma 3n E4B	827	±10	4.4K	4.7%	2.0%	30 tps	0.5s	8K	$0.01	$0.02
240	252	Ministral 3B	824	±18	2.3K	4.9%	0.8%	248 tps	0.4s	131K	$0.08	$0.08
241	240	Ministral 8B	823	±23	2.2K	5.4%	1.4%	177 tps	0.4s	128K	$0.14	$0.14
242	210	GLM 4.7 Flash	822	±30	490	3.9%	5.8%	61 tps	2.8s	128K	$0.07	$0.39
243	252	Gemma 3 1B	807	±16	1.9K	5.9%	0.6%	176 tps	1.0s	33K	$0.06	$0.10
244	252	GPT-3.5 Turbo Instruct	802	±15	2K	2.7%	<0.1%	46 tps	1.2s	4K	$1.50	$2.00
245	240	DeepSeek-R1 Distill Llama 70B	798	±14	2.7K	5.5%	3.6%	27 tps	1.6s	32K	$0.73	$0.95
246	240	LFM2 2.6B	796	±22	645	10.4%	6.7%	184 tps	0.4s	33K	$0.01	$0.02
247	240	GLM 4.5 Flash	796	±49	490	8.4%	12.2%	15 tps	2.2s	131K	$0	$0
248	262	Mistral Small	789	±16	1.1K	4.6%	1.7%	142 tps	0.6s	32K	$0.43	$1.30
249	262	Open Mistral 7B	788	±19	1.3K	4.8%	0.7%	176 tps	0.4s	33K	$0.25	$0.25
250	234	ERNIE 4.5 21B A3B Thinking	779	±27	895	7.3%	1.8%	87 tps	1.5s	120K	$0.07	$0.28
251	262	Command R	777	±18	2K	3.8%	5.8%	54 tps	0.6s	128K	$0.30	$0.99
252	252	Mistral Large	771	±25	1K	5.1%	1.5%	54 tps	0.7s	33K	$2.00	$6.00
253	262	Baichuan-M2-32B	769	±32	705	11.3%	<0.1%	32 tps	3.3s	131K	$0.07	$0.07
254	269	Gemma 3 4B	762	±13	3.3K	4.6%	1.3%	138 tps	0.7s	131K	$0.02	$0.04
255	269	Pixtral 12B	758	±27	2.5K	5.7%	2.2%	101 tps	1.2s	131K	$0.08	$0.08
256	269	Mixtral 8x22B Instruct	754	±25	1.3K	4.8%	1.8%	142 tps	0.7s	66K	$0.45	$0.45
257	269	Command R+	753	±16	1.5K	4.9%	2.8%	36 tps	0.7s	128K	$2.08	$9.45
258	262	Qwen 2.5 VL 72B Instruct	748	±18	1.8K	5.7%	5.3%	25 tps	3.7s	128K	$1.01	$2.79
259	269	Inflection 3 Pi	744	±19	1.5K	4.2%	1.1%	33 tps	3.4s	8K	$2.50	$10.00
260	276	Hermes 3 405B Instruct	739	±23	1.4K	3.9%	2.3%	20 tps	1.1s	131K	$0.80	$0.80
261	262	Hermes 4 405B Reasoning FP8	732	±24	2.1K	14.5%	3.6%	32 tps	0.8s	131K	$1.00	$3.00
262	269	Inflection 3 Productivity	721	±20	1.5K	4.8%	0.6%	50 tps	3.2s	8K	$2.50	$10.00
263	262	Goliath 120B	686	±28	625	5.3%	2.7%	21 tps	2.2s	6K	$6.56	$9.38
264	269	DeepHermes 3 Mistral 24B Preview	677	±31	635	5.9%	2.5%	50 tps	1.0s	33K	$0.06	$0.25
265	276	DeepSeek-R1 Distill Qwen 32B	672	±17	1.6K	5.4%	6.2%	22 tps	1.8s	131K	$0.37	$0.39
266	276	MiniMax M1	653	±16	2.9K	6.1%	<0.1%	31 tps	2.8s	1M	$0.55	$2.20
267	279	Phi 4 Mini Instruct	629	±26	1K	6.9%	7.4%	40 tps	1.1s	128K	$0.07	$0.30
268	279	UI-TARS 1.5 7B	620	±40	485	11.8%	4.0%	75 tps	0.9s	128K	$0.10	$0.20
269	279	MythoMax L2 13B	618	±20	2.3K	5.8%	1.2%	22 tps	1.1s	4K	$0.18	$0.18
270	279	Phi 4 Reasoning	600	±11	1.9K	5.0%	21.0%	29 tps	1.0s	33K	$0.06	$0.25
271	279	Hunyuan A13B Instruct	574	±20	1.5K	9.3%	2.3%	67 tps	2.0s	33K	$0.01	$0.01
272	284	Qwen 2.5 VL 3B Instruct	564	±27	3.4K	4.9%	3.0%	44 tps	2.5s	128K	$0.21	$0.63
273	286	Phi 4 Mini Reasoning	411	±18	2.9K	12.7%	9.7%	30 tps	0.9s	128K	$0.07	$0.30

Show Less