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.

956
Gemma 3 12B
956
GLM 4.7 Flash
954
Rnj-1 Instruct
954
Devstral Small
952
Qwen3.5 9B FP8
950
GPT-3.5 Turbo
948
Grok 3 Mini
947
Krutrim 2
944
Jamba 1.5 Large
944
Qwen 2.5 14B Instruct
938
Llama 3.3 Swallow 70B Instruct
932
GPT-4o mini
930
ERNIE 4.5 21B A3B Thinking
928
Moonshot V1 Auto
926
GPT-3.5 Turbo Instruct

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
161214Gemma 3 12B956±39.8K1.9%4.2%73 tps0.8s131K$0.05$0.12
162179GLM 4.7 Flash956±84.8K1.8%5.8%61 tps2.8s128K$0.07$0.39
163222Rnj-1 Instruct954±63K3.7%0.6%103 tps0.3s33K$0.15$0.15
164201Devstral Small954±65.4K2.4%2.4%180 tps0.6s131K$0.10$0.30
165209Qwen3.5 9B FP8952±194953.9%5.8%64 tps0.7s256K$0.10$0.15
166209GPT-3.5 Turbo950±26K1.0%1.3%74 tps0.9s16K$0.75$1.75
167186Grok 3 Mini948±228.5K3.9%1.2%43 tps0.5s131K$0.30$0.50
168214Krutrim 2947±211.8K0.6%12.5%33 tps2.1s128K$1.00$1.00
169222Jamba 1.5 Large944±313.6K1.6%1.7%48 tps0.9s256K$1.50$6.00
170209Qwen 2.5 14B Instruct944±39K2.3%2.4%40 tps1.6s1M$0.40$1.61
171209Llama 3.3 Swallow 70B Instruct938±310.7K3.2%1.4%153 tps1.3s131K$0.13$0.39
172201GPT-4o mini932±49K3.4%2.1%71 tps1.7s128K$0.15$0.60
173229ERNIE 4.5 21B A3B Thinking930±62.7K3.6%1.8%87 tps1.5s120K$0.07$0.28
174229Moonshot V1 Auto928±64K1.6%1.2%54 tps1.5s8K$2.00$5.00
175240GPT-3.5 Turbo Instruct926±38K1.4%<0.1%46 tps1.2s4K$1.50$2.00
176225GPT-3.5 Turbo 16k923±310.7K1.6%<0.1%22 tps0.6s16K$3.00$4.00
177214Moonshot V1 128k917±54.7K1.7%1.4%54 tps1.5s131K$2.00$5.00
178229Krutrim Spectre V2912±47.4K1.1%<0.1%33 tps3.1s4K$0.19$0.19
179240Moonshot V1 8k911±64K1.8%1.0%55 tps1.5s8K$0.20$2.00
180246WizardLM-2 8x22B911±29.8K1.1%11.6%11 tps2.5s66K$0.77$0.77
181235GLM 4 32B904±211.7K2.1%2.6%40 tps1.6s33K$0.14$0.14
182246Mixtral 8x22B903±55.2K2.1%1.2%140 tps0.6s64K$2.00$6.00
183253GPT-4 Turbo903±137854.3%4.7%21 tps1.9s128K$10.00$30.00
184214OpenAI o3-mini-high901±315.8K3.0%2.4%231 tps10.5s200K$1.10$4.40
185256Solar Mini 250422901±53.7K4.4%1.8%90 tps1.7s33K$0.15$0.15
186265Ministral 3B 2512900±111.7K3.5%2.8%339 tps0.6s131K$0.10$0.10
187260Apriel 1.6 15B Thinker898±111.1K2.1%2.6%92 tps0.4s131K$0$0
188240Hermes 4 405B FP8897±102.1K5.6%3.5%31 tps0.9s131K$0.52$1.73
189240Moonshot V1 32k893±54K1.2%1.4%53 tps1.4s33K$1.00$3.00
190229Magistral Medium 2509887±56.2K6.2%4.0%58 tps0.9s131K$2.00$5.00
191265Inflection 3 Productivity883±47K1.7%0.6%50 tps3.2s8K$2.50$10.00
192260Open Mistral 7B879±35.4K2.4%0.7%176 tps0.4s33K$0.25$0.25
193246Hermes 4 70B878±91.3K4.3%1.1%67 tps0.6s131K$0.12$0.39
194265Magistral Small 2509876±73.4K4.8%2.7%116 tps0.6s131K$0.50$1.50
195265LFM2 2.6B863±52.2K6.3%6.7%184 tps0.4s33K$0.01$0.02
196271Inflection 3 Pi862±37.3K1.4%1.1%33 tps3.4s8K$2.50$10.00
197271Mistral Large851±54.7K2.5%1.5%54 tps0.7s33K$2.00$6.00
198274DeepHermes 3 Mistral 24B Preview850±121.7K4.7%2.5%50 tps1.0s33K$0.06$0.25
199265Qwen 2.5 VL 72B Instruct849±102.6K6.3%5.3%25 tps3.7s128K$1.01$2.79
200274LFM2 8B A1B831±72.3K6.7%<0.1%142 tps0.3s33K$0.01$0.02
View All (208 models)