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

902

Gemma 3 27B

889

C4AI Aya Expanse 32B

872

Command R

868

Ministral 8B

866

Mixtral 8x22B Instruct

858

Mistral Small 3 24B Instruct

844

Hermes 4 405B Reasoning FP8

837

GLM 4.6V Flash

828

Command R+

828

Pixtral 12B

827

Gemma 3 4B

823

Qwen 2.5 7B

818

Open Mistral Nemo

815

Mixtral 8x7B Instruct

808

Command R 7B

Last updated about 1 month ago

Rank	Overall	Name	VIBE Score	Confidence Interval	Votes	Downvote %	Abort %	Speed	Latency	Context	Cost (Input)	Cost (Output)
41	186	Gemma 3 27B	902	±18	615	13.4%	1.8%	35 tps	1.1s	66K	$0.06	$0.10
42	214	C4AI Aya Expanse 32B	889	±11	1.3K	10.0%	1.5%	43 tps	0.5s	128K	$0.50	$1.50
43	225	Command R	872	±16	770	12.5%	5.8%	54 tps	0.6s	128K	$0.30	$0.99
44	229	Ministral 8B	868	±15	800	13.5%	1.4%	177 tps	0.4s	128K	$0.14	$0.14
45	246	Mixtral 8x22B Instruct	866	±31	570	10.2%	1.8%	142 tps	0.7s	66K	$0.45	$0.45
46	194	Mistral Small 3 24B Instruct	858	±18	585	12.7%	2.6%	77 tps	0.6s	33K	$0.07	$0.14
47	260	Hermes 4 405B Reasoning FP8	844	±12	2.1K	18.8%	3.6%	32 tps	0.8s	131K	$1.00	$3.00
48	186	GLM 4.6V Flash	837	±9	2K	9.0%	3.7%	64 tps	2.1s	128K	$0.04	$0.40
49	235	Command R+	828	±21	665	10.1%	2.8%	36 tps	0.7s	128K	$2.08	$9.45
50	274	Pixtral 12B	828	±11	2.2K	6.8%	2.2%	101 tps	1.2s	131K	$0.08	$0.08
51	235	Gemma 3 4B	827	±11	1.2K	9.9%	1.3%	138 tps	0.7s	131K	$0.02	$0.04
52	214	Qwen 2.5 7B	823	±15	685	11.6%	3.7%	40 tps	1.9s	131K	$0.08	$0.27
53	225	Open Mistral Nemo	818	±24	590	12.6%	1.5%	171 tps	0.5s	131K	$0.15	$0.15
54	256	Mixtral 8x7B Instruct	815	±28	510	12.1%	0.2%	79 tps	0.7s	33K	$0.23	$0.31
55	225	Command R 7B	808	±13	1.3K	12.9%	1.1%	76 tps	0.4s	128K	$0.04	$0.15
56	235	Mixtral 8x7B	801	±29	525	12.5%	2.2%	142 tps	0.6s	33K	$0.23	$0.23
57	260	Mistral Small	799	±23	465	12.3%	1.7%	142 tps	0.6s	32K	$0.43	$1.30
58	271	Hermes 3 405B Instruct	792	±21	490	10.1%	2.3%	20 tps	1.1s	131K	$0.80	$0.80
59	256	Phi 4	780	±17	565	11.7%	5.1%	28 tps	1.3s	128K	$0.10	$0.32
60	246	Ministral 3B	772	±17	785	12.3%	0.8%	248 tps	0.4s	131K	$0.08	$0.08
61	256	Gemma 3 1B	758	±23	965	13.1%	0.6%	176 tps	1.0s	33K	$0.06	$0.10
62	201	Mistral Small 24B Instruct	752	±22	480	15.0%	1.5%	84 tps	0.4s	33K	$0.80	$0.80
63	253	Gemma 2 27B	727	±15	585	11.4%	1.4%	44 tps	1.4s	8K	$0.80	$0.80
64	265	Mixtral-8x7B Instruct v0.1	675	±39	465	12.3%	1.3%	54 tps	0.4s	33K	$0.60	$0.60
65	288	Qwen 2.5 VL 3B Instruct	670	±12	2.5K	9.2%	3.0%	44 tps	2.5s	128K	$0.21	$0.63
66	281	MythoMax L2 13B	569	±32	785	15.1%	1.2%	22 tps	1.1s	4K	$0.18	$0.18
67	291	Phi 4 Mini Reasoning	475	±12	1.9K	22.5%	9.7%	30 tps	0.9s	128K	$0.07	$0.30

2of2

View All (67 models)