Leaderboard | Text

Models

Topics

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.

Open license models

Filter the leaderboard to only show models that have an open license.

755

Pixtral 12B

739

Hunyuan A13B Instruct

697

Phi 4 Reasoning

688

MiniMax M1

667

UI-TARS 1.5 7B

635

Phi 4 Mini Reasoning

630

LFM2.5 1.2B Thinking

629

Qwen 2.5 VL 3B Instruct

Last updated about 1 month ago

Rank	Overall	Name	VIBE Score	Confidence Interval	Votes	Downvote %	Abort %	Speed	Latency	Context	Cost (Input)	Cost (Output)
281	274	Pixtral 12B	755	±12	4.6K	5.7%	2.2%	101 tps	1.2s	131K	$0.08	$0.08
282	285	Hunyuan A13B Instruct	739	±5	4.6K	5.0%	2.3%	67 tps	2.0s	33K	$0.01	$0.01
283	287	Phi 4 Reasoning	697	±8	4K	3.5%	21.0%	29 tps	1.0s	33K	$0.06	$0.25
284	284	MiniMax M1	688	±4	7.8K	4.0%	<0.1%	31 tps	2.8s	1M	$0.55	$2.20
285	289	UI-TARS 1.5 7B	667	±18	1.4K	8.7%	4.0%	75 tps	0.9s	128K	$0.10	$0.20
286	291	Phi 4 Mini Reasoning	635	±4	7.9K	7.9%	9.7%	30 tps	0.9s	128K	$0.07	$0.30
287	291	LFM2.5 1.2B Thinking	630	±22	705	4.7%	2.6%	258 tps	0.4s	33K	$0	$0
288	288	Qwen 2.5 VL 3B Instruct	629	±7	5.1K	6.8%	3.0%	44 tps	2.5s	128K	$0.21	$0.63

8of8