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.

905
Qwen3 235B A22B Thinking 2507
904
DeepSeek-R1 0528
902
Gemini 2.0 Flash Lite
901
GPT-5 Nano
896
GPT-4.1 nano
891
GPT-5 Mini High
890
Qwen3 Next 80B A3B Thinking
885
Gemini 2.0 Flash
873
ERNIE 4.5 300B A47B
863
Qwen3 32B Fast
847
Qwen Turbo
842
DeepSeek V3.2 Speciale
838
Llama 4 Maverick
837
GLM 4.6V
832
Qwen3 30B A3B

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
121124Qwen3 235B A22B Thinking 2507905±166952.1%2.5%53 tps1.6s131K$0.59$5.70
122133DeepSeek-R1 0528904±196404.5%1.3%93 tps0.5s64K$1.60$3.67
123143Gemini 2.0 Flash Lite902±149907.9%<0.1%42 tps0.5s1M$0.08$0.30
124157GPT-5 Nano901±91.2K5.0%3.2%113 tps20.9s400K$0.05$0.40
125133GPT-4.1 nano896±111.8K3.2%0.6%175 tps0.5s1M$0.10$0.40
126241GPT-5 Mini High891±168104.1%<0.1%33 tps3.9s400K$0.25$2.00
127157Qwen3 Next 80B A3B Thinking890±161.1K3.4%0.6%175 tps1.3s256K$0.21$2.26
128143Gemini 2.0 Flash885±168705.9%<0.1%76 tps0.5s1M$0.14$0.56
129119ERNIE 4.5 300B A47B873±121.1K3.4%4.7%23 tps2.3s123K$0.28$1.10
130121Qwen3 32B Fast863±132K4.5%11.6%30 tps3.1s41K$0.10$0.25
131159Qwen Turbo847±151.1K4.3%<0.1%53 tps1.1s1M$0.05$0.20
132133DeepSeek V3.2 Speciale842±384854.9%6.0%43 tps1.4s131K$0.84$1.52
133161Llama 4 Maverick838±102.4K4.3%1.2%88 tps2.4s1M$0.23$0.83
134139GLM 4.6V837±236405.2%6.4%21 tps1.8s128K$0.38$0.90
135126Qwen3 30B A3B832±209504.0%5.1%163 tps1.0s41K$0.06$0.21
136121QwQ 32B825±161.3K5.5%5.4%41 tps2.1s16K$0.43$0.56
137165Qwen3 4B818±208704.9%1.9%94 tps1.5s128K$0.01$0.01
138161Qwen3 8B813±236105.4%2.4%61 tps1.4s41K$0.02$0.07
139314MAI-DS-R1810±205655.8%<0.1%73 tps3.2s64K$0.10$0.40
140213Claude Haiku 3.5801±151.2K5.9%0.8%40 tps2.8s200K$0.80$4.00
141186Grok 3 Mini799±231.9K2.6%1.2%43 tps0.5s131K$0.30$0.50
142302YouTube797±201.1K4.0%<0.1%34 tps2.7s32K$0.99$0.99
143165Pixtral Large796±266107.6%2.5%57 tps1.3s128K$1.50$4.50
144170Mistral Small 3.2 24B793±284755.9%2.8%141 tps0.7s33K$0.02$0.08
145148Qwen3 30B A3B Thinking 2507787±146554.4%0.5%124 tps1.2s131K$0.16$1.70
146160Llama 4 Scout782±151.6K4.1%0.6%88 tps5.1s131K$0.18$0.46
147214OpenAI o3-mini-high778±176303.1%2.4%231 tps10.5s200K$1.10$4.40
148177OpenAI o3-mini777±122K3.6%0.8%143 tps3.3s200K$1.10$4.40
149229Magistral Medium 2509765±186103.9%4.0%58 tps0.9s131K$2.00$5.00
150175OpenAI o3-mini-low752±171.4K4.3%0.7%139 tps1.5s200K$1.10$4.40
151186Grok 3 Mini Fast724±151.3K4.3%1.6%44 tps0.5s131K$0.60$4.00
152194Llama 3.3 70B719±185503.5%0.3%500 tps0.5s8K$0.48$0.66
153277Wikipedia703±167104.1%<0.1%47 tps2.1s32K$0$0
154274Pixtral 12B674±337205.9%2.2%101 tps1.2s131K$0.08$0.08
155265Qwen 2.5 VL 72B Instruct635±345055.6%5.3%25 tps3.7s128K$1.01$2.79
156179Inception Mercury613±255006.5%0.4%257 tps1.1s32K$0.25$1.00
157182Fauna Fox518±296256.0%<0.1%194 tps0.3s128K$0.04$0.15
158288Qwen 2.5 VL 3B Instruct373±469557.7%3.0%44 tps2.5s128K$0.21$0.63
159292AFM 4.5B95±546059.7%<0.1%81 tps0.3s66K$0.05$0.20
View All (159 models)