Models
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.

823
Ministral 8B
822
GLM 4.7 Flash
807
Gemma 3 1B
802
GPT-3.5 Turbo Instruct
798
DeepSeek-R1 Distill Llama 70B
796
LFM2 2.6B
796
GLM 4.5 Flash
789
Mistral Small
788
Open Mistral 7B
779
ERNIE 4.5 21B A3B Thinking
777
Command R
771
Mistral Large
769
Baichuan-M2-32B
762
Gemma 3 4B
758
Pixtral 12B

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
241240Ministral 8B823±232.2K5.4%1.4%177 tps0.4s128K$0.14$0.14
242210GLM 4.7 Flash822±304903.9%5.8%61 tps2.8s128K$0.07$0.39
243252Gemma 3 1B807±161.9K5.9%0.6%176 tps1.0s33K$0.06$0.10
244252GPT-3.5 Turbo Instruct802±152K2.7%<0.1%46 tps1.2s4K$1.50$2.00
245240DeepSeek-R1 Distill Llama 70B798±142.7K5.5%3.6%27 tps1.6s32K$0.73$0.95
246240LFM2 2.6B796±2264510.4%6.7%184 tps0.4s33K$0.01$0.02
247240GLM 4.5 Flash796±494908.4%12.2%15 tps2.2s131K$0$0
248262Mistral Small789±161.1K4.6%1.7%142 tps0.6s32K$0.43$1.30
249262Open Mistral 7B788±191.3K4.8%0.7%176 tps0.4s33K$0.25$0.25
250234ERNIE 4.5 21B A3B Thinking779±278957.3%1.8%87 tps1.5s120K$0.07$0.28
251262Command R777±182K3.8%5.8%54 tps0.6s128K$0.30$0.99
252252Mistral Large771±251K5.1%1.5%54 tps0.7s33K$2.00$6.00
253262Baichuan-M2-32B769±3270511.3%<0.1%32 tps3.3s131K$0.07$0.07
254269Gemma 3 4B762±133.3K4.6%1.3%138 tps0.7s131K$0.02$0.04
255269Pixtral 12B758±272.5K5.7%2.2%101 tps1.2s131K$0.08$0.08
256269Mixtral 8x22B Instruct754±251.3K4.8%1.8%142 tps0.7s66K$0.45$0.45
257269Command R+753±161.5K4.9%2.8%36 tps0.7s128K$2.08$9.45
258262Qwen 2.5 VL 72B Instruct748±181.8K5.7%5.3%25 tps3.7s128K$1.01$2.79
259269Inflection 3 Pi744±191.5K4.2%1.1%33 tps3.4s8K$2.50$10.00
260276Hermes 3 405B Instruct739±231.4K3.9%2.3%20 tps1.1s131K$0.80$0.80
261262Hermes 4 405B Reasoning FP8732±242.1K14.5%3.6%32 tps0.8s131K$1.00$3.00
262269Inflection 3 Productivity721±201.5K4.8%0.6%50 tps3.2s8K$2.50$10.00
263262Goliath 120B686±286255.3%2.7%21 tps2.2s6K$6.56$9.38
264269DeepHermes 3 Mistral 24B Preview677±316355.9%2.5%50 tps1.0s33K$0.06$0.25
265276DeepSeek-R1 Distill Qwen 32B672±171.6K5.4%6.2%22 tps1.8s131K$0.37$0.39
266276MiniMax M1653±162.9K6.1%<0.1%31 tps2.8s1M$0.55$2.20
267279Phi 4 Mini Instruct629±261K6.9%7.4%40 tps1.1s128K$0.07$0.30
268279UI-TARS 1.5 7B620±4048511.8%4.0%75 tps0.9s128K$0.10$0.20
269279MythoMax L2 13B618±202.3K5.8%1.2%22 tps1.1s4K$0.18$0.18
270279Phi 4 Reasoning600±111.9K5.0%21.0%29 tps1.0s33K$0.06$0.25
271279Hunyuan A13B Instruct574±201.5K9.3%2.3%67 tps2.0s33K$0.01$0.01
272284Qwen 2.5 VL 3B Instruct564±273.4K4.9%3.0%44 tps2.5s128K$0.21$0.63
273286Phi 4 Mini Reasoning411±182.9K12.7%9.7%30 tps0.9s128K$0.07$0.30
View All (273 models)