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.

1000
Amazon Nova Micro 1.0
1002
Devstral Small 2507
1004
Gemini 2.0 Flash
1005
Mistral Small 3.1
1005
GLM 4.5 Flash
1005
Qwen 2.5 32B Instruct
1005
GLM 4.6V
1006
Mistral Small 3.2 24B Instruct
1006
ERNIE 4.5 21B A3B
1007
OpenAI o4-mini
1007
Qwen3 Max Thinking
1009
Qwen3 VL 30B A3B Instruct
1009
MiMo V2 Flash
1009
OpenAI o4-mini-high
1010
Seed 2.0 Mini (Medium)

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
121246Amazon Nova Micro 1.01000±236302.3%4.1%193 tps0.6s128K$0.04$0.07
122170Devstral Small 25071002±89802.0%2.2%186 tps0.5s131K$0.10$0.30
123143Gemini 2.0 Flash1004±323.8K0.9%<0.1%76 tps0.5s1M$0.14$0.56
124161Mistral Small 3.11005±39.4K1.0%7.4%13 tps2.6s32K$0.17$0.28
125194GLM 4.5 Flash1005±111.1K2.3%12.2%15 tps2.2s131K$0$0
126153Qwen 2.5 32B Instruct1005±315.7K1.0%2.5%48 tps1.0s131K$0.21$0.25
127139GLM 4.6V1005±37.4K1.4%6.4%21 tps1.8s128K$0.38$0.90
128186Mistral Small 3.2 24B Instruct1006±71.6K3.4%1.9%113 tps1.1s131K$0.02$0.08
129165ERNIE 4.5 21B A3B1006±71.4K1.8%2.3%78 tps1.5s120K$0.05$0.19
130139OpenAI o4-mini1007±313.6K2.2%1.4%97 tps7.0s128K$1.10$4.40
131129Qwen3 Max Thinking1007±56.9K1.4%13.5%32 tps2.3s256K$1.20$6.00
132139Qwen3 VL 30B A3B Instruct1009±91.2K4.5%1.8%80 tps2.6s129K$0.18$0.67
133175MiMo V2 Flash1009±106453.7%7.2%24 tps1.9s262K$0.07$0.23
134148OpenAI o4-mini-high1009±219.5K2.1%1.9%117 tps15.9s200K$1.10$4.40
135139Seed 2.0 Mini (Medium)1010±101.3K2.6%11.9%33 tps1.7s256K$0.15$0.60
136179Baichuan-M2-32B1011±81.4K2.7%<0.1%32 tps3.3s131K$0.07$0.07
137101Qwen3.5 35B A3B1011±151.1K1.4%2.1%116 tps2.1s256K$0.63$1.13
138133GPT-4.1 nano1014±252.1K1.3%0.6%175 tps0.5s1M$0.10$0.40
139157Qwen3 Next 80B A3B Thinking1015±312.3K2.3%0.6%175 tps1.3s256K$0.21$2.26
140133Kimi K2 09051016±49.2K2.1%4.0%30 tps1.4s262K$0.63$2.39
141148OpenAI o31018±64.2K1.8%0.9%85 tps6.8s128K$7.33$29.33
142143Seed 1.6 2506151018±43.6K1.6%3.1%46 tps2.2s256K$0.25$2.00
143161Qwen3 8B1020±56.1K2.6%2.4%61 tps1.4s41K$0.02$0.07
144143Mistral Medium 31023±91.2K1.7%2.4%47 tps0.8s33K$0.40$2.00
14586Claude Sonnet 41026±288.9K1.5%1.8%49 tps1.3s200K$3.00$15.00
146165Qwen3 VL 30B A3B Thinking1027±72.3K4.6%4.5%84 tps2.9s127K$0.20$1.47
147126DeepSeek V31027±241.8K1.0%0.9%69 tps1.1s64K$0.59$1.49
148165Qwen3 4B1027±49.4K3.3%1.9%94 tps1.5s128K$0.01$0.01
149133DeepSeek V3.2 Speciale1027±55.9K2.2%6.0%43 tps1.4s131K$0.84$1.52
150126Qwen3 VL 235B A22B Thinking1027±47.3K2.9%4.3%47 tps3.0s127K$0.47$3.31
151111Grok 3 Fast1030±312K1.1%1.7%52 tps2.4s131K$5.00$25.00
152129Command A1030±267.4K1.3%2.2%42 tps0.8s256K$2.00$7.33
153153Ministral 14B 3.01031±62.3K3.1%2.0%119 tps0.5s128K$0.20$0.20
154118GPT-4.1 mini1031±257.7K1.3%1.1%67 tps0.9s1M$0.34$1.60
155148Qwen3 30B A3B Thinking 25071035±44K1.4%0.5%124 tps1.2s131K$0.16$1.70
156106Claude Sonnet 3.5 v21035±416.6K1.0%<0.1%46 tps1.4s200K$3.00$15.00
157124Kimi K2 0905 Turbo1037±318.8K2.4%0.7%373 tps0.5s262K$1.70$6.50
15884MiniMax M2.51038±111.5K2.0%1.4%70 tps1.9s205K$0.28$1.20
15986Seed 2.0 Lite (Medium)1043±91.2K2.0%6.6%33 tps1.6s256K$0.25$2.00
160113Mistral Medium1044±233.2K1.3%1.8%48 tps0.6s33K$1.48$4.55
View All (283 models)