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.

1169
Kimi K2.5
1160
Kimi K2 Thinking Turbo
1145
Grok 3 Beta
1141
Qwen3 Next 80B A3B Instruct
1128
MiniMax M2.5 Lightning
1124
Qwen3.5 122B A17B
1124
Kimi K2.5 Instant
1117
DeepSeek V3.2 Thinking
1108
Mistral Large 3
1086
gpt-oss-120b
1082
Qwen3.5 27B
1079
Step 3.5 Flash
1079
DeepSeek V3.2 Exp Chat
1074
Qwen3 235B A22B
1063
DeepSeek V3.2 Exp Thinking

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
133Kimi K2.51169±65.3K2.8%6.5%33 tps1.7s262K$0.34$2.57
244Kimi K2 Thinking Turbo1160±813.2K3.5%2.0%75 tps1.4s262K$1.15$8.00
3104Grok 3 Beta1145±91.8K0.6%<0.1%58 tps0.8s131K$3.00$15.00
433Qwen3 Next 80B A3B Instruct1141±47.6K7.7%0.6%84 tps1.1s256K$0.20$1.42
579MiniMax M2.5 Lightning1128±149952.5%1.5%51 tps2.0s205K$0.60$2.40
652Qwen3.5 122B A17B1124±171.1K3.2%1.5%82 tps1.4s256K$0.40$3.20
737Kimi K2.5 Instant1124±131.4K2.4%2.9%32 tps3.0s262K$0.50$3.00
856DeepSeek V3.2 Thinking1117±610K3.8%9.0%30 tps2.6s131K$0.28$0.42
965Mistral Large 31108±74K6.3%2.1%51 tps1.0s256K$0.50$1.50
1048gpt-oss-120b1086±415.1K7.5%0.7%213 tps0.5s131K$0.11$0.50
1181Qwen3.5 27B1082±265502.7%3.7%55 tps2.6s256K$0.30$2.40
1248Step 3.5 Flash1079±236452.3%2.2%109 tps0.6s256K$0.05$0.15
1365DeepSeek V3.2 Exp Chat1079±44.3K8.8%2.6%29 tps1.5s131K$0.27$0.39
1486Qwen3 235B A22B1074±102.8K14.4%5.3%71 tps0.9s41K$0.23$0.63
1595DeepSeek V3.2 Exp Thinking1063±85K3.4%7.2%26 tps3.0s131K$0.28$0.42
16106DeepSeek V3.1 Terminus Thinking1047±72.5K11.6%5.9%27 tps1.8s131K$0.56$1.68
17165Pixtral Large1042±82.5K5.1%2.5%57 tps1.3s128K$1.50$4.50
1895DeepSeek-R1 Turbo1032±101.4K5.5%2.6%29 tps1.8s64K$2.85$4.75
19129Command A1029±511K8.4%2.2%42 tps0.8s256K$2.00$7.33
20126DeepSeek V31028±75.9K5.7%0.9%69 tps1.1s64K$0.59$1.49
21200NVIDIA Llama 3.1 Nemotron 70B1018±82.4K5.9%<0.1%9 tps0.1s128K$0.33$0.39
22139Qwen3 VL 30B A3B Instruct1012±171K6.5%1.8%80 tps2.6s129K$0.18$0.67
23113Kimi K2 Fast1006±426.2K13.8%0.8%365 tps0.5s131K$1.00$3.00
24219NVIDIA Llama 3.3 Nemotron Super 49B v11002±131.2K9.7%<0.1%13 tpsN/A131K$0.07$0.20
25200K2 Think999±141.1K6.2%<0.1%418 tps2.8sN/A$0$0
26170Llama 3.1 8B Turbo998±121.1K2.8%2.1%650 tps0.5s128K$0.13$0.14
27133DeepSeek-R1 0528983±121.3K4.6%1.3%93 tps0.5s64K$1.60$3.67
28201Gemma 3 27B IT983±1590510.4%2.0%60 tps0.8s128K$0.17$0.29
29241Arcee AI Blitz979±136105.4%<0.1%6 tpsN/A33K$0.45$0.75
30265Llama 3.1 405B Instruct Turbo973±1862510.1%<0.1%26 tps0.8s131K$3.50$3.50
31222Sky T1 32B Preview972±1680510.6%7.8%73 tps0.6s16K$0.12$0.18
32177Mistral Small 3.1 24B Instruct966±121K10.6%7.5%15 tps2.4s131K$0.06$0.18
33161Mistral Small 3.1960±1691511.2%7.4%13 tps2.6s32K$0.17$0.28
34302OLMo 2 0425 1B Instruct956±195701.7%<0.1%68 tps0.0s4K$0$0
35161Llama 4 Maverick956±411.2K8.2%1.2%88 tps2.4s1M$0.23$0.83
36121QwQ 32B955±75K15.3%5.4%41 tps2.1s16K$0.43$0.56
37101gpt-oss-20b954±56.1K10.8%0.5%216 tps0.5s131K$0.06$0.26
38165Qwen3 VL 30B A3B Thinking949±81.5K11.2%4.5%84 tps2.9s127K$0.20$1.47
39194Llama 3.2 11B Instruct943±1474514.4%1.5%152 tps0.5s8K$0.16$0.16
40126Qwen3 30B A3B939±53.7K12.1%5.1%163 tps1.0s41K$0.06$0.21
View All (78 models)