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.

1031
Grok 4 Fast Non-Reasoning
1031
Claude Sonnet 4 (Thinking)
1023
GPT-5
1020
GPT-5.2 (Extra High)
1020
Claude Sonnet 3.7
1012
Gemini 2.5 Flash Lite
1007
MiniMax M2.1
996
Grok 3
992
Kimi K2 Fast
989
Grok 4
988
Grok 4 Fast Reasoning
986
Gemini 2.5 Flash Lite Thinking
983
Solar Pro 2 250710
979
GPT-5 Mini
976
ERNIE 4.5 300B A47B

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
4152Grok 4 Fast Non-Reasoning1031±296000.8%1.5%93 tps0.6s2M$0.27$0.67
4248Claude Sonnet 4 (Thinking)1031±207751.3%1.5%52 tps1.5s200K$3.00$13.67
4352GPT-51023±141.1K1.7%3.1%78 tps23.1s400K$1.25$9.67
4442GPT-5.2 (Extra High) 1020±246000.8%13.2%17 tps20.5s400K$1.75$14.00
45111Claude Sonnet 3.71020±161.3K1.5%<0.1%39 tps1.6s200K$3.00$15.00
46101Gemini 2.5 Flash Lite1012±161.5K2.2%1.3%210 tps0.7s1M$0.10$0.40
4760MiniMax M2.11007±209551.0%2.1%66 tps2.6s205K$0.30$1.20
48106Grok 3996±121.5K1.6%1.5%53 tps0.6s1M$3.67$18.33
49113Kimi K2 Fast992±103.5K2.8%0.8%365 tps0.5s131K$1.00$3.00
5068Grok 4989±113.3K0.9%3.9%29 tps11.1s256K$3.00$15.00
5148Grok 4 Fast Reasoning988±176350.8%2.1%102 tps3.1s2M$0.30$0.75
52113Gemini 2.5 Flash Lite Thinking986±195801.7%1.0%118 tps4.4s1M$0.03$0.13
53133Solar Pro 2 250710983±237453.9%<0.1%9 tpsN/A66K$0.50$0.50
5471GPT-5 Mini979±275350.9%2.6%66 tps14.2s400K$0.25$2.00
55119ERNIE 4.5 300B A47B976±151.2K2.0%4.7%23 tps2.3s123K$0.28$1.10
5695Gemini 2.5 Flash976±143.7K1.6%1.3%2 tps3.7s1M$0.30$2.50
57126DeepSeek V3974±161.5K1.4%0.9%69 tps1.1s64K$0.59$1.49
5862MiniMax M2974±217601.3%2.2%39 tps2.3s205K$0.21$0.85
5971Gemini 2.5 Flash Lite Preview 0925968±186801.4%1.2%209 tps0.7s1M$0.25$0.35
60121QwQ 32B968±206501.5%5.4%41 tps2.1s16K$0.43$0.56
6160Gemini 2.5 Flash Preview 0925964±247001.4%1.2%5 tps0.9s1M$0.13$0.97
62118GPT-4.1 mini963±131.9K1.3%1.1%67 tps0.9s1M$0.34$1.60
6386Claude Sonnet 4958±123.4K1.0%1.8%49 tps1.3s200K$3.00$15.00
6444Kimi K2 Thinking Turbo954±285051.0%2.0%75 tps1.4s262K$1.15$8.00
65160Llama 4 Scout947±141.6K1.9%0.6%88 tps5.1s131K$0.18$0.46
66124Kimi K2 0905 Turbo946±197951.9%0.7%373 tps0.5s262K$1.70$6.50
67133GPT-4.1 nano944±131.5K2.0%0.6%175 tps0.5s1M$0.10$0.40
6868GLM 4.7933±208701.7%5.8%40 tps1.5s200K$0.77$1.73
69170Kimi K2 0711925±205103.8%1.6%29 tps1.3s131K$0.72$2.60
70129Command A924±172K2.0%2.2%42 tps0.8s256K$2.00$7.33
71159Qwen Turbo924±198052.4%<0.1%53 tps1.1s1M$0.05$0.20
72139OpenAI o4-mini917±156502.3%1.4%97 tps7.0s128K$1.10$4.40
7348OpenAI o1-mini914±237301.4%<0.1%118 tpsN/A128K$1.13$4.51
7465Mistral Large 3911±305353.6%2.1%51 tps1.0s256K$0.50$1.50
75113Mistral Medium908±218451.7%1.8%48 tps0.6s33K$1.48$4.55
7679Qwen3 Max Thinking Preview903±335350.9%3.1%40 tps2.1s256K$1.20$6.00
7771Seed 1.8 251228894±256601.5%3.7%41 tps2.1s256K$0.25$2.00
78161Llama 4 Maverick890±142.2K1.8%1.2%88 tps2.4s1M$0.23$0.83
79143Gemini 2.0 Flash887±236802.2%<0.1%76 tps0.5s1M$0.14$0.56
8071Gemini 2.5 Flash Thinking886±226301.6%2.2%88 tps6.4s1M$0.30$2.50
View All (88 models)