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.

305
AFM 4.5B
546
Qwen 2.5 VL 3B Instruct
552
DeepSeek-R1 0528 Qwen3 8B
621
GPT-5 Nano Minimal
682
Wikipedia
715
Fauna Fox
726
GLM 4.6V Flash
739
Grok 3 Mini
744
Pixtral 12B
745
Llama 3.3 70B
778
Pixtral Large
779
Qwen Turbo
781
Gemma 3n E4B
790
Magistral Small 2509
796
GPT-5 Mini Low

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
1292AFM 4.5B305±465855.6%<0.1%81 tps0.3s66K$0.05$0.20
2288Qwen 2.5 VL 3B Instruct546±311K9.1%3.0%44 tps2.5s128K$0.21$0.63
3314DeepSeek-R1 0528 Qwen3 8B552±235655.8%<0.1%45 tps2.4s128K$0.05$0.09
4292GPT-5 Nano Minimal621±185907.8%<0.1%88 tps0.8s400K$0.05$0.40
5277Wikipedia682±345509.8%<0.1%47 tps2.1s32K$0$0
6182Fauna Fox715±284904.9%<0.1%194 tps0.3s128K$0.04$0.15
7186GLM 4.6V Flash726±295752.5%3.7%64 tps2.1s128K$0.04$0.40
8186Grok 3 Mini739±201.4K2.5%1.2%43 tps0.5s131K$0.30$0.50
9274Pixtral 12B744±339409.6%2.2%101 tps1.2s131K$0.08$0.08
10194Llama 3.3 70B745±305254.5%0.3%500 tps0.5s8K$0.48$0.66
11165Pixtral Large778±181.1K7.2%2.5%57 tps1.3s128K$1.50$4.50
12159Qwen Turbo779±158602.8%<0.1%53 tps1.1s1M$0.05$0.20
13186Gemma 3n E4B781±275354.5%2.0%30 tps0.5s8K$0.01$0.02
14265Magistral Small 2509790±295306.2%2.7%116 tps0.6s131K$0.50$1.50
15108GPT-5 Mini Low796±168657.0%<0.1%69 tps3.2s400K$0.25$2.00
16229Magistral Medium 2509797±175705.0%4.0%58 tps0.9s131K$2.00$5.00
17147Arcee AI Maestro Reasoning802±174804.0%<0.1%85 tps0.3s131K$0.90$3.30
18265Qwen 2.5 VL 72B Instruct804±297156.5%5.3%25 tps3.7s128K$1.01$2.79
19213DeepSeek R1T Chimera805±255103.8%<0.1%46 tps1.1s164K$0.09$0.36
20148Qwen3 30B A3B Thinking 2507818±187953.0%0.5%124 tps1.2s131K$0.16$1.70
2186Nemotron 3 Nano (Thinking)821±235404.4%2.0%200 tps0.5s256K$0$0
22201GPT-4o mini826±186456.5%2.1%71 tps1.7s128K$0.15$0.60
23161Qwen3 8B827±366004.0%2.4%61 tps1.4s41K$0.02$0.07
24133DeepSeek V3.2 Speciale830±285403.6%6.0%43 tps1.4s131K$0.84$1.52
25186Grok 3 Mini Fast832±231K3.3%1.6%44 tps0.5s131K$0.60$4.00
2684GPT-5 Mini Minimal835±131.1K6.6%1.2%63 tps1.4s400K$0.25$2.00
27175OpenAI o3-mini-low838±211.7K2.6%0.7%139 tps1.5s200K$1.10$4.40
28157GPT-5 Nano843±142K6.0%3.2%113 tps20.9s400K$0.05$0.40
29157Qwen3 Next 80B A3B Thinking846±151.3K3.9%0.6%175 tps1.3s256K$0.21$2.26
30121Qwen3 32B Fast853±131.8K4.2%11.6%30 tps3.1s41K$0.10$0.25
31133Qwen3 14B856±247452.6%1.7%109 tps0.8s41K$0.04$0.15
32170Kimi K2 0711858±248904.3%1.6%29 tps1.3s131K$0.72$2.60
33139GLM 4.6V865±248902.7%6.4%21 tps1.8s128K$0.38$0.90
34129Qwen3 Max Thinking866±141.5K1.7%13.5%32 tps2.3s256K$1.20$6.00
35214OpenAI o3-mini-high868±131.4K3.8%2.4%231 tps10.5s200K$1.10$4.40
36246DeepSeek-R1 Distill Llama 70B869±285904.8%3.6%27 tps1.6s32K$0.73$0.95
37179GLM 4.7 Flash874±248552.8%5.8%61 tps2.8s128K$0.07$0.39
38160Llama 4 Scout875±152.3K2.9%0.6%88 tps5.1s131K$0.18$0.46
39270Solar Pro 2 250710 (Reasoning)878±255053.8%<0.1%9 tpsN/A66K$0.50$0.50
40165Qwen3 4B878±237353.9%1.9%94 tps1.5s128K$0.01$0.01
View All (188 models)