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

1169

Kimi K2.5

1160

Kimi K2 Thinking Turbo

1141

Qwen3 Next 80B A3B Instruct

1128

MiniMax M2.5 Lightning

1124

Qwen3.5 122B A17B

1124

Kimi K2.5 Instant

1117

DeepSeek V3.2 Thinking

1108

Mistral Large 3

1086

gpt-oss-120b

1082

Qwen3.5 27B

1079

Step 3.5 Flash

1079

DeepSeek V3.2 Exp Chat

1074

Qwen3 235B A22B

1063

DeepSeek V3.2 Exp Thinking

1047

DeepSeek V3.1 Terminus 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	33	Kimi K2.5	1169	±6	5.3K	2.8%	6.5%	33 tps	1.7s	262K	$0.34	$2.57
2	44	Kimi K2 Thinking Turbo	1160	±8	13.2K	3.5%	2.0%	75 tps	1.4s	262K	$1.15	$8.00
3	33	Qwen3 Next 80B A3B Instruct	1141	±4	7.6K	7.7%	0.6%	84 tps	1.1s	256K	$0.20	$1.42
4	79	MiniMax M2.5 Lightning	1128	±14	995	2.5%	1.5%	51 tps	2.0s	205K	$0.60	$2.40
5	52	Qwen3.5 122B A17B	1124	±17	1.1K	3.2%	1.5%	82 tps	1.4s	256K	$0.40	$3.20
6	37	Kimi K2.5 Instant	1124	±13	1.4K	2.4%	2.9%	32 tps	3.0s	262K	$0.50	$3.00
7	56	DeepSeek V3.2 Thinking	1117	±6	10K	3.8%	9.0%	30 tps	2.6s	131K	$0.28	$0.42
8	65	Mistral Large 3	1108	±7	4K	6.3%	2.1%	51 tps	1.0s	256K	$0.50	$1.50
9	48	gpt-oss-120b	1086	±4	15.1K	7.5%	0.7%	213 tps	0.5s	131K	$0.11	$0.50
10	81	Qwen3.5 27B	1082	±26	550	2.7%	3.7%	55 tps	2.6s	256K	$0.30	$2.40
11	48	Step 3.5 Flash	1079	±23	645	2.3%	2.2%	109 tps	0.6s	256K	$0.05	$0.15
12	65	DeepSeek V3.2 Exp Chat	1079	±4	4.3K	8.8%	2.6%	29 tps	1.5s	131K	$0.27	$0.39
13	86	Qwen3 235B A22B	1074	±10	2.8K	14.4%	5.3%	71 tps	0.9s	41K	$0.23	$0.63
14	95	DeepSeek V3.2 Exp Thinking	1063	±8	5K	3.4%	7.2%	26 tps	3.0s	131K	$0.28	$0.42
15	106	DeepSeek V3.1 Terminus Thinking	1047	±7	2.5K	11.6%	5.9%	27 tps	1.8s	131K	$0.56	$1.68
16	165	Pixtral Large	1042	±8	2.5K	5.1%	2.5%	57 tps	1.3s	128K	$1.50	$4.50
17	95	DeepSeek-R1 Turbo	1032	±10	1.4K	5.5%	2.6%	29 tps	1.8s	64K	$2.85	$4.75
18	129	Command A	1029	±5	11K	8.4%	2.2%	42 tps	0.8s	256K	$2.00	$7.33
19	126	DeepSeek V3	1028	±7	5.9K	5.7%	0.9%	69 tps	1.1s	64K	$0.59	$1.49
20	139	Qwen3 VL 30B A3B Instruct	1012	±17	1K	6.5%	1.8%	80 tps	2.6s	129K	$0.18	$0.67
21	113	Kimi K2 Fast	1006	±4	26.2K	13.8%	0.8%	365 tps	0.5s	131K	$1.00	$3.00
22	170	Llama 3.1 8B Turbo	998	±12	1.1K	2.8%	2.1%	650 tps	0.5s	128K	$0.13	$0.14
23	133	DeepSeek-R1 0528	983	±12	1.3K	4.6%	1.3%	93 tps	0.5s	64K	$1.60	$3.67
24	201	Gemma 3 27B IT	983	±15	905	10.4%	2.0%	60 tps	0.8s	128K	$0.17	$0.29
25	222	Sky T1 32B Preview	972	±16	805	10.6%	7.8%	73 tps	0.6s	16K	$0.12	$0.18
26	177	Mistral Small 3.1 24B Instruct	966	±12	1K	10.6%	7.5%	15 tps	2.4s	131K	$0.06	$0.18
27	161	Mistral Small 3.1	960	±16	915	11.2%	7.4%	13 tps	2.6s	32K	$0.17	$0.28
28	161	Llama 4 Maverick	956	±4	11.2K	8.2%	1.2%	88 tps	2.4s	1M	$0.23	$0.83
29	121	QwQ 32B	955	±7	5K	15.3%	5.4%	41 tps	2.1s	16K	$0.43	$0.56
30	101	gpt-oss-20b	954	±5	6.1K	10.8%	0.5%	216 tps	0.5s	131K	$0.06	$0.26
31	165	Qwen3 VL 30B A3B Thinking	949	±8	1.5K	11.2%	4.5%	84 tps	2.9s	127K	$0.20	$1.47
32	194	Llama 3.2 11B Instruct	943	±14	745	14.4%	1.5%	152 tps	0.5s	8K	$0.16	$0.16
33	126	Qwen3 30B A3B	939	±5	3.7K	12.1%	5.1%	163 tps	1.0s	41K	$0.06	$0.21
34	148	DeepSeek-R1	939	±12	1.6K	5.5%	0.8%	133 tps	0.6s	64K	$0.91	$3.07
35	86	Nemotron 3 Nano (Thinking)	938	±14	1.3K	7.6%	2.0%	200 tps	0.5s	256K	$0	$0
36	133	Qwen3 14B	933	±11	2.7K	17.1%	1.7%	109 tps	0.8s	41K	$0.04	$0.15
37	121	Qwen3 32B Fast	932	±5	4.5K	12.9%	11.6%	30 tps	3.1s	41K	$0.10	$0.25
38	153	Qwen 2.5 32B Instruct	916	±9	1.9K	18.0%	2.5%	48 tps	1.0s	131K	$0.21	$0.25
39	214	Llama 3.3 70B Instruct Turbo	914	±24	640	11.7%	2.0%	78 tps	1.0s	131K	$0.88	$0.88
40	246	DeepSeek-R1 Distill Llama 70B	907	±23	535	7.0%	3.6%	27 tps	1.6s	32K	$0.73	$0.95

1of2

View All (67 models)