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.

1207
MiniMax M2.7-highspeed
1171
Kimi K2.5 Instant
1164
Step 3.5 Flash
1161
Qwen3 Next 80B A3B Instruct
1151
Qwen3.5 122B A17B
1151
Kimi K2.5
1144
gpt-oss-120b
1137
Kimi K2 Thinking Turbo
1127
DeepSeek V3.2 Thinking
1127
Nemotron 3 Nano (Thinking)
1124
DeepSeek V3.2 Exp Chat
1122
Mistral Large 3
1121
MiniMax M2.5 Lightning
1097
Qwen3.5 27B
1093
gpt-oss-20b

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
122MiniMax M2.7-highspeed1207±101.1K2.1%2.3%50 tps2.1s205K$0.60$2.40
237Kimi K2.5 Instant1171±46.2K1.8%2.9%32 tps3.0s262K$0.50$3.00
348Step 3.5 Flash1164±54K1.5%2.2%109 tps0.6s256K$0.05$0.15
433Qwen3 Next 80B A3B Instruct1161±224.9K3.8%0.6%84 tps1.1s256K$0.20$1.42
552Qwen3.5 122B A17B1151±44.7K1.6%1.5%82 tps1.4s256K$0.40$3.20
633Kimi K2.51151±332.5K1.8%6.5%33 tps1.7s262K$0.34$2.57
748gpt-oss-120b1144±240.7K3.7%0.7%213 tps0.5s131K$0.11$0.50
844Kimi K2 Thinking Turbo1137±329.8K2.5%2.0%75 tps1.4s262K$1.15$8.00
956DeepSeek V3.2 Thinking1127±337.6K2.6%9.0%30 tps2.6s131K$0.28$0.42
1086Nemotron 3 Nano (Thinking)1127±37.5K2.4%2.0%200 tps0.5s256K$0$0
1165DeepSeek V3.2 Exp Chat1124±314.3K4.0%2.6%29 tps1.5s131K$0.27$0.39
1265Mistral Large 31122±314.3K3.3%2.1%51 tps1.0s256K$0.50$1.50
1379MiniMax M2.5 Lightning1121±45.6K1.3%1.5%51 tps2.0s205K$0.60$2.40
1481Qwen3.5 27B1097±62.3K2.4%3.7%55 tps2.6s256K$0.30$2.40
15101gpt-oss-20b1093±220.3K4.6%0.5%216 tps0.5s131K$0.06$0.26
16104Grok 3 Beta1092±38.1K0.6%<0.1%58 tps0.8s131K$3.00$15.00
1786Qwen3 235B A22B1090±311.9K5.1%5.3%71 tps0.9s41K$0.23$0.63
18159Llama 3.1 405B Instruct1072±81.7K2.0%<0.1%52 tps0.5s128K$2.60$4.27
19106DeepSeek V3.1 Terminus Thinking1071±38.5K4.9%5.9%27 tps1.8s131K$0.56$1.68
2095DeepSeek-R1 Turbo1069±37.3K2.9%2.6%29 tps1.8s64K$2.85$4.75
2195DeepSeek V3.2 Exp Thinking1068±39.9K2.7%7.2%26 tps3.0s131K$0.28$0.42
22121QwQ 32B1068±228.3K4.4%5.4%41 tps2.1s16K$0.43$0.56
23200Llama 3 8B Turbo1066±62.7K1.3%<0.1%97 tps0.1s8K$0.12$0.13
24121Qwen3 32B Fast1059±225K3.8%11.6%30 tps3.1s41K$0.10$0.25
25177Llama 3 70B Turbo1058±218.1K0.8%<0.1%31 tps0.0s8K$0.73$0.83
26126Qwen3 30B A3B1051±215.1K4.4%5.1%163 tps1.0s41K$0.06$0.21
27200K2 Think1047±44.7K2.1%<0.1%418 tps2.8sN/A$0$0
28182Qwen 2.5 72B Turbo1044±73K2.6%<0.1%84 tps0.8s131K$0.60$0.60
29129Command A1039±282.1K2.2%2.2%42 tps0.8s256K$2.00$7.33
30133Qwen3 14B1037±212.5K5.7%1.7%109 tps0.8s41K$0.04$0.15
31113Kimi K2 Fast1037±2107.2K4.5%0.8%365 tps0.5s131K$1.00$3.00
32126DeepSeek V31035±257.9K1.7%0.9%69 tps1.1s64K$0.59$1.49
33170Llama 3.1 8B Turbo1027±38.2K1.4%2.1%650 tps0.5s128K$0.13$0.14
34139Qwen3 VL 30B A3B Instruct1022±72.1K4.8%1.8%80 tps2.6s129K$0.18$0.67
35133DeepSeek-R1 05281020±312.3K2.1%1.3%93 tps0.5s64K$1.60$3.67
36165Qwen3 VL 30B A3B Thinking1020±43.5K6.5%4.5%84 tps2.9s127K$0.20$1.47
37200NVIDIA Llama 3.1 Nemotron 70B1016±223.2K1.0%<0.1%9 tps0.1s128K$0.33$0.39
38219NVIDIA Llama 3.3 Nemotron Super 49B v11012±215.5K1.1%<0.1%13 tpsN/A131K$0.07$0.20
39153Qwen 2.5 32B Instruct1011±316.8K3.1%2.5%48 tps1.0s131K$0.21$0.25
40161Mistral Small 3.11006±39.7K2.0%7.4%13 tps2.6s32K$0.17$0.28
View All (111 models)