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

373

Qwen 2.5 VL 3B Instruct

674

Pixtral 12B

796

Pixtral Large

825

QwQ 32B

832

Qwen3 30B A3B

838

Llama 4 Maverick

863

Qwen3 32B Fast

904

DeepSeek-R1 0528

909

DeepSeek V3.2 Exp Chat

912

gpt-oss-20b

936

DeepSeek-R1

943

Qwen3 14B

948

Command A

956

DeepSeek V3

979

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	288	Qwen 2.5 VL 3B Instruct	373	±46	955	7.7%	3.0%	44 tps	2.5s	128K	$0.21	$0.63
2	274	Pixtral 12B	674	±33	720	5.9%	2.2%	101 tps	1.2s	131K	$0.08	$0.08
3	165	Pixtral Large	796	±26	610	7.6%	2.5%	57 tps	1.3s	128K	$1.50	$4.50
4	121	QwQ 32B	825	±16	1.3K	5.5%	5.4%	41 tps	2.1s	16K	$0.43	$0.56
5	126	Qwen3 30B A3B	832	±20	950	4.0%	5.1%	163 tps	1.0s	41K	$0.06	$0.21
6	161	Llama 4 Maverick	838	±10	2.4K	4.3%	1.2%	88 tps	2.4s	1M	$0.23	$0.83
7	121	Qwen3 32B Fast	863	±13	2K	4.5%	11.6%	30 tps	3.1s	41K	$0.10	$0.25
8	133	DeepSeek-R1 0528	904	±19	640	4.5%	1.3%	93 tps	0.5s	64K	$1.60	$3.67
9	65	DeepSeek V3.2 Exp Chat	909	±11	1.3K	2.6%	2.6%	29 tps	1.5s	131K	$0.27	$0.39
10	101	gpt-oss-20b	912	±12	1.5K	4.1%	0.5%	216 tps	0.5s	131K	$0.06	$0.26
11	148	DeepSeek-R1	936	±21	705	4.1%	0.8%	133 tps	0.6s	64K	$0.91	$3.07
12	133	Qwen3 14B	943	±16	825	4.1%	1.7%	109 tps	0.8s	41K	$0.04	$0.15
13	129	Command A	948	±12	1.9K	3.1%	2.2%	42 tps	0.8s	256K	$2.00	$7.33
14	126	DeepSeek V3	956	±12	1.7K	2.5%	0.9%	69 tps	1.1s	64K	$0.59	$1.49
15	106	DeepSeek V3.1 Terminus Thinking	979	±13	660	3.6%	5.9%	27 tps	1.8s	131K	$0.56	$1.68
16	44	Kimi K2 Thinking Turbo	986	±14	1.1K	3.2%	2.0%	75 tps	1.4s	262K	$1.15	$8.00
17	86	Qwen3 235B A22B	989	±19	740	3.9%	5.3%	71 tps	0.9s	41K	$0.23	$0.63
18	113	Kimi K2 Fast	989	±10	7.4K	2.2%	0.8%	365 tps	0.5s	131K	$1.00	$3.00
19	95	DeepSeek V3.2 Exp Thinking	999	±22	775	1.9%	7.2%	26 tps	3.0s	131K	$0.28	$0.42
20	95	DeepSeek-R1 Turbo	1021	±13	485	3.0%	2.6%	29 tps	1.8s	64K	$2.85	$4.75
21	65	Mistral Large 3	1026	±22	1.1K	4.1%	2.1%	51 tps	1.0s	256K	$0.50	$1.50
22	56	DeepSeek V3.2 Thinking	1033	±15	1.7K	2.0%	9.0%	30 tps	2.6s	131K	$0.28	$0.42
23	48	gpt-oss-120b	1083	±7	3.5K	3.0%	0.7%	213 tps	0.5s	131K	$0.11	$0.50
24	33	Kimi K2.5	1083	±16	1.7K	3.2%	6.5%	33 tps	1.7s	262K	$0.34	$2.57
25	37	Kimi K2.5 Instant	1101	±28	495	1.0%	2.9%	32 tps	3.0s	262K	$0.50	$3.00
26	33	Qwen3 Next 80B A3B Instruct	1142	±9	1.8K	2.5%	0.6%	84 tps	1.1s	256K	$0.20	$1.42