Models
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.

523
Qwen 2.5 VL 3B Instruct
696
DeepSeek-R1 Distill Qwen 32B
746
Qwen 2.5 VL 72B Instruct
831
Qwen 2.5 7B
861
Qwen 2.5 14B Instruct
870
Qwen 2.5 7B Turbo
880
Qwen3 4B
948
Qwen3 8B
953
Qwen3 30B A3B Thinking 2507
960
Qwen 2.5 72B
962
Qwen3 14B
967
Qwen3 VL 30B A3B Thinking
972
Qwen 2.5 32B Instruct
994
Qwen3 30B A3B
1000
Qwen3 235B A22B Thinking 2507

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
1284Qwen 2.5 VL 3B Instruct523±254.1K6.1%3.0%44 tps2.5s128K$0.21$0.63
2276DeepSeek-R1 Distill Qwen 32B696±202K5.5%6.2%22 tps1.8s131K$0.37$0.39
3262Qwen 2.5 VL 72B Instruct746±202.1K6.0%5.3%25 tps3.7s128K$1.01$2.79
4240Qwen 2.5 7B831±172K5.1%3.7%40 tps1.9s131K$0.08$0.27
5210Qwen 2.5 14B Instruct861±162.4K5.7%2.4%40 tps1.6s1M$0.40$1.61
6210Qwen 2.5 7B Turbo870±256156.1%0.5%125 tps0.4s131K$0.30$0.30
7210Qwen3 4B880±85.1K9.6%1.9%94 tps1.5s128K$0.01$0.01
8179Qwen3 8B948±94.2K8.2%2.4%61 tps1.4s41K$0.02$0.07
9179Qwen3 30B A3B Thinking 2507953±103.5K4.7%0.5%124 tps1.2s131K$0.16$1.70
10167Qwen 2.5 72B960±151.4K4.5%1.2%96 tps1.2s131K$0.14$0.26
11167Qwen3 14B962±85.3K8.4%1.7%109 tps0.8s41K$0.04$0.15
12167Qwen3 VL 30B A3B Thinking967±111.9K8.9%4.5%84 tps2.9s127K$0.20$1.47
13167Qwen 2.5 32B Instruct972±74.1K6.5%2.5%48 tps1.0s131K$0.21$0.25
14148Qwen3 30B A3B994±86.3K6.9%5.1%163 tps1.0s41K$0.06$0.21
15148Qwen3 235B A22B Thinking 25071000±102.8K4.4%2.5%53 tps1.6s131K$0.59$5.70
16148Qwen 2.5 VL 32B Instruct1001±218654.9%6.3%43 tps3.2s128K$0.35$0.62
17148Qwen3 Coder Plus1007±226104.7%5.1%56 tps2.3s128K$1.80$9.80
18148Qwen3 VL 235B A22B Thinking1009±64.6K8.3%4.3%47 tps3.0s127K$0.47$3.31
19135Qwen3 VL 30B A3B Instruct1034±151K6.7%1.8%80 tps2.6s129K$0.18$0.67
20135Qwen3 Next 80B A3B Thinking1035±56.2K7.4%0.6%175 tps1.3s256K$0.21$2.26
21135QwQ 32B1035±411.6K6.4%5.4%41 tps2.1s16K$0.43$0.56
22128Qwen3 32B1044±198506.6%3.9%30 tps3.1s41K$0.12$0.42
23119Qwen3 32B Fast1052±611.4K5.2%11.6%30 tps3.1s41K$0.10$0.25
24105Qwen3 Max Thinking1080±181.5K2.0%13.5%32 tps2.3s256K$1.20$6.00
25105Qwen3 Omni 30B A3B Instruct1085±137754.3%3.9%65 tps1.2s66K$0.35$0.97
2698Qwen3 235B A22B1093±64.5K8.0%5.3%71 tps0.9s41K$0.23$0.63
2790Qwen3 Coder 480B A35B Instruct1099±83.1K4.5%3.3%61 tps2.0s262K$0.71$1.34
2890Qwen Max1107±418.3K4.2%1.5%49 tps1.5s33K$1.60$6.40
2985Qwen3 Omni 30B A3B Thinking1110±102.3K6.0%3.7%67 tps1.2s66K$0.97$1.79
3077Qwen3 Max Thinking Preview1127±106.3K5.7%3.1%40 tps2.1s256K$1.20$6.00
3174Qwen3.5 397B A17B1142±142.5K2.9%4.3%57 tps1.4s256K$0.52$3.00
3274Qwen Plus (Aug'24)1146±517.2K4.7%1.4%53 tps1.3s30K$0.40$1.20
3369Qwen3.5 35B A3B1164±258653.9%2.1%116 tps2.1s256K$0.63$1.13
3460Qwen3 235B A22B Instruct 25071172±412.6K6.4%6.8%13 tps1.9s262K$0.13$0.52
3549Qwen3 30B A3B Instruct 25071194±512.7K5.7%1.2%55 tps1.3s131K$0.13$0.72
3643Qwen3 Max Instruct Preview1203±616.1K4.6%1.1%31 tps1.7s256K$1.43$6.61
3736Qwen3.5 27B1211±169104.7%3.7%55 tps2.6s256K$0.30$2.40
3836Qwen3.5 122B A17B1216±151.9K3.1%1.5%82 tps1.4s256K$0.40$3.20
3936Qwen3 VL 235B A22B Instruct1220±75.6K6.7%3.1%75 tps1.9s129K$0.37$1.81
4031Qwen3 Next 80B A3B Instruct1231±58.8K5.8%0.6%84 tps1.1s256K$0.20$1.42