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.

949
GLM 4.7
950
OpenAI o4-mini-high
956
DeepSeek V3
957
DeepSeek V3.1 Turbo
958
DeepSeek V3.1 Thinking
960
OpenAI o3
968
GPT-5 Mini Minimal
969
GLM 4.5
976
GPT-4.1 mini
979
DeepSeek V3.1 Terminus Thinking
985
Kimi K2 Thinking
986
Kimi K2 Thinking Turbo
989
Mistral Medium
989
Qwen3 235B A22B
989
Kimi K2 Fast

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
4168GLM 4.7949±131.6K1.8%5.8%40 tps1.5s200K$0.77$1.73
42148OpenAI o4-mini-high950±121.5K3.8%1.9%117 tps15.9s200K$1.10$4.40
43126DeepSeek V3956±121.7K2.5%0.9%69 tps1.1s64K$0.59$1.49
4456DeepSeek V3.1 Turbo957±148204.1%0.9%173 tps1.3s164K$2.00$3.75
45129DeepSeek V3.1 Thinking958±141K2.4%7.1%18 tps1.8s131K$0.23$0.75
46148OpenAI o3960±166002.4%0.9%85 tps6.8s128K$7.33$29.33
4784GPT-5 Mini Minimal968±177953.6%1.2%63 tps1.4s400K$0.25$2.00
48113GLM 4.5969±191.3K3.5%3.7%46 tps1.4s131K$0.43$1.63
49118GPT-4.1 mini976±132.7K1.8%1.1%67 tps0.9s1M$0.34$1.60
50106DeepSeek V3.1 Terminus Thinking979±136603.6%5.9%27 tps1.8s131K$0.56$1.68
5195Kimi K2 Thinking985±216203.1%4.2%61 tps5.9s262K$0.24$1.03
5244Kimi K2 Thinking Turbo986±141.1K3.2%2.0%75 tps1.4s262K$1.15$8.00
53113Mistral Medium989±141.1K2.7%1.8%48 tps0.6s33K$1.48$4.55
5486Qwen3 235B A22B989±197403.9%5.3%71 tps0.9s41K$0.23$0.63
55113Kimi K2 Fast989±107.4K2.2%0.8%365 tps0.5s131K$1.00$3.00
56106DeepSeek V3 0324990±112.1K3.0%5.8%12 tps2.7s164K$0.38$0.93
57124Kimi K2 0905 Turbo991±121.6K1.8%0.7%373 tps0.5s262K$1.70$6.50
58113Gemini 2.5 Flash Lite Thinking996±112.5K3.7%1.0%118 tps4.4s1M$0.03$0.13
5995DeepSeek V3.2 Exp Thinking999±227751.9%7.2%26 tps3.0s131K$0.28$0.42
60170Kimi K2 07111002±157203.4%1.6%29 tps1.3s131K$0.72$2.60
61106Grok 31003±92K2.6%1.5%53 tps0.6s1M$3.67$18.33
6286Amazon Nova 2 Lite1013±188154.7%1.0%137 tps0.6s300K$0.35$2.95
63101Gemini 2.5 Flash Lite1014±95.3K3.9%1.3%210 tps0.7s1M$0.10$0.40
64133Kimi K2 09051014±138102.4%4.0%30 tps1.4s262K$0.63$2.39
6586DeepSeek V3.1 Chat1018±121.1K3.1%2.8%21 tps1.6s131K$0.38$1.00
6679Qwen3 Max Thinking Preview1020±101.2K2.4%3.1%40 tps2.1s256K$1.20$6.00
6793Qwen Max1021±141.8K2.7%1.5%49 tps1.5s33K$1.60$6.40
6895DeepSeek-R1 Turbo1021±134853.0%2.6%29 tps1.8s64K$2.85$4.75
6965Mistral Large 31026±221.1K4.1%2.1%51 tps1.0s256K$0.50$1.50
70129Qwen3 Max Thinking1029±316002.4%13.5%32 tps2.3s256K$1.20$6.00
7156DeepSeek V3.2 Thinking1033±151.7K2.0%9.0%30 tps2.6s131K$0.28$0.42
7244DeepSeek V3.1 Terminus Chat1037±91.3K2.2%3.4%27 tps1.5s131K$0.86$1.80
7365GLM 4.61041±111.6K2.9%5.4%39 tps1.5s200K$0.42$1.66
7462MiniMax M21043±91.8K4.2%2.2%39 tps2.3s205K$0.21$0.85
7595Gemini 2.5 Flash Lite Thinking Preview 09251044±91.7K3.5%1.5%152 tps3.0s1M$0.10$0.40
7660MiniMax M2.11044±121.7K2.8%2.1%66 tps2.6s205K$0.30$1.20
7781GPT-4o1046±151.4K2.5%1.0%49 tps2.4s128K$3.71$12.57
7852Grok 4 Fast Non-Reasoning1054±81.6K2.5%1.5%93 tps0.6s2M$0.27$0.67
7952Claude Haiku 4.51057±63.4K3.4%1.1%100 tps0.9s200K$1.00$5.00
8040DeepSeek V3.21063±161.1K2.5%1.4%83 tps5.1s131K$0.43$1.09
View All (133 models)