Models
Topics
Language
More

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.

Open license models

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

908
Grok 3 Mini
901
Qwen 2.5 7B
900
Llama 3.3 70B
899
Devstral Medium
899
GLM 4.6V Flash
892
Gemma 3n E4B
891
GPT-5 Mini High
890
Pixtral Large
888
NVIDIA Llama 3.1 Nemotron Ultra 253B v1
885
Llama 3.1 405B Instruct Turbo
885
GLM Z1 32B
882
Wikipedia
876
Switchpoint Router
869
Llama 3.1 70B Instruct Turbo
866
ERNIE 4.5 21B A3B Thinking

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
201186Grok 3 Mini908±93.8K2.3%1.2%43 tps0.5s131K$0.30$0.50
202214Qwen 2.5 7B901±194904.9%3.7%40 tps1.9s131K$0.08$0.27
203194Llama 3.3 70B900±121.1K3.0%0.3%500 tps0.5s8K$0.48$0.66
204170Devstral Medium899±109951.5%1.5%77 tps0.6s131K$0.40$2.00
205186GLM 4.6V Flash899±151.3K2.3%3.7%64 tps2.1s128K$0.04$0.40
206186Gemma 3n E4B892±102K2.6%2.0%30 tps0.5s8K$0.01$0.02
207241GPT-5 Mini High891±101.4K2.8%<0.1%33 tps3.9s400K$0.25$2.00
208165Pixtral Large890±126404.5%2.5%57 tps1.3s128K$1.50$4.50
209292NVIDIA Llama 3.1 Nemotron Ultra 253B v1888±225750.9%<0.1%40 tps0.8s128K$0.30$0.90
210265Llama 3.1 405B Instruct Turbo885±225603.4%<0.1%26 tps0.8s131K$3.50$3.50
211277GLM Z1 32B885±141.1K2.2%<0.1%18 tps9.3s33K$0.09$0.11
212277Wikipedia882±102.8K3.7%<0.1%47 tps2.1s32K$0$0
213179Switchpoint Router876±166751.5%1.7%71 tps4.9s131K$0.85$3.40
214233Llama 3.1 70B Instruct Turbo869±199952.0%<0.1%110 tps0.8s128K$0.88$0.88
215229ERNIE 4.5 21B A3B Thinking866±166852.8%1.8%87 tps1.5s120K$0.07$0.28
216324Solar Pro 3856±205201.0%2.0%99 tps1.3s131K$0.15$0.60
217209Llama 3.3 Swallow 70B Instruct854±188901.1%1.4%153 tps1.3s131K$0.13$0.39
218200NVIDIA Llama 3.1 Nemotron 70B851±191.3K1.1%<0.1%9 tps0.1s128K$0.33$0.39
219229Magistral Medium 2509849±169903.9%4.0%58 tps0.9s131K$2.00$5.00
220194Magistral Small 2506847±141.3K1.9%1.6%156 tps0.5s40K$0.37$1.10
221374Cogito V2 671B839±131.3K3.0%<0.1%41 tps0.6s164K$1.25$1.25
222161Mistral Small 3.1835±176751.5%7.4%13 tps2.6s32K$0.17$0.28
223209Qwen 2.5 14B Instruct830±245701.7%2.4%40 tps1.6s1M$0.40$1.61
224270AFM 4.5B Preview830±228752.2%<0.1%32 tps0.0s66K$0$0
225265Magistral Small 2509830±238255.7%2.7%116 tps0.6s131K$0.50$1.50
226179Inception Mercury829±102K1.5%0.4%257 tps1.1s32K$0.25$1.00
227260Hermes 4 405B Reasoning FP8828±111.3K3.7%3.6%32 tps0.8s131K$1.00$3.00
228201Llama 3 8B826±177201.4%6.0%85 tps0.7s8K$0.12$0.16
229235Gemma 3 4B825±147553.2%1.3%138 tps0.7s131K$0.02$0.04
230222Jamba 1.5 Large819±156901.4%1.7%48 tps0.9s256K$1.50$6.00
231194Llama 3.2 11B Instruct816±225252.8%1.5%152 tps0.5s8K$0.16$0.16
232241Claude Haiku 3813±186452.3%0.4%62 tps0.5s200K$0.25$1.25
233270Arcee AI Virtuoso-Medium809±215400.9%<0.1%3 tpsN/A131K$0.50$0.80
234179Amazon Nova Pro 1.0807±191.4K1.7%0.9%96 tps0.7s300K$0.80$1.70
235201GPT-4o mini803±245454.4%2.1%71 tps1.7s128K$0.15$0.60
236222Sky T1 32B Preview797±176251.6%7.8%73 tps0.6s16K$0.12$0.18
237292Arcee AI Spotlight796±151.4K1.8%<0.1%121 tps0.4s131K$0.18$0.18
238219Arcee AI Virtuoso-Large791±118401.8%<0.1%64 tps0.5s131K$0.75$1.20
239314MAI-DS-R1778±121.7K3.4%<0.1%73 tps3.2s64K$0.10$0.40
240225Command R 7B775±188701.7%1.1%76 tps0.4s128K$0.04$0.15
View All (260 models)