Models

Choose model family

Claude by AnthropicGPT by OpenAIGemini by GoogleGrok by xAIQwen by AlibabaMistral by Mistral AILlama by MetaDeepSeekGLM by Z.aiKimi by Moonshot AI
Topics

Choose topic

All topics
Facts and InformationCreative Writing and IdeationLogic and Problem-SolvingTask CompletionCoding
Language

Choose language

All languagesEnglishChineseArabicSpanishIndonesianJapanese
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.

All
Single turnMultiple turns
Open license models

Filter the leaderboard to only show models that have an open license.

All selected
Open licenseProprietary license
700
Kimi K2 Fast
712
Gemini 2.5 Flash
868
Grok 4
900
Claude Sonnet 4
944
Gemini 2.5 Pro
1066
Gemini 3 Pro
1297
GPT-5 Chat

Last updated about 1 month ago

RankOverallNameVIBE
Score		Confidence
Interval		VotesDownvote %Abort %SpeedLatencyContextCost
(Input)		Cost
(Output)
1113Kimi K2 Fast700±1616600.8%0.8%365 tps0.5s131K$1.00$3.00
295Gemini 2.5 Flash712±1816400.8%1.3%2 tps3.7s1M$0.30$2.50
368Grok 4868±1357701.9%3.9%29 tps11.1s256K$3.00$15.00
486Claude Sonnet 4900±1467301.4%1.8%49 tps1.3s200K$3.00$15.00
544Gemini 2.5 Pro944±1016501.5%2.3%45 tps2.6s1M$1.25$10.00
610Gemini 3 Pro1066±2197400.7%2.1%50 tps3.6s1M$2.00$12.00
722GPT-5 Chat1297±836001.6%1.3%95 tps0.9s400K$1.25$10.00