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.

1185
Qwen3 Next 80B A3B Instruct
1182
gpt-oss-120b
1158
Kimi K2.5 Instant
1150
Step 3.5 Flash
1147
Kimi K2.5
1145
Kimi K2 Thinking Turbo
1144
DeepSeek V3.2 Thinking
1133
Mistral Large 3
1129
Qwen3 235B A22B
1125
DeepSeek V3.2 Exp Chat
1123
Nemotron 3 Nano (Thinking)
1123
Qwen3.5 122B A17B
1104
DeepSeek-R1 Turbo
1088
Qwen3 14B
1084
DeepSeek V3.2 Exp Thinking

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
133Qwen3 Next 80B A3B Instruct1185±219.8K1.9%0.6%84 tps1.1s256K$0.20$1.42
248gpt-oss-120b1182±226.3K1.3%0.7%213 tps0.5s131K$0.11$0.50
337Kimi K2.5 Instant1158±64K1.5%2.9%32 tps3.0s262K$0.50$3.00
448Step 3.5 Flash1150±62.9K1.7%2.2%109 tps0.6s256K$0.05$0.15
533Kimi K2.51147±316.1K1.2%6.5%33 tps1.7s262K$0.34$2.57
644Kimi K2 Thinking Turbo1145±210.9K1.6%2.0%75 tps1.4s262K$1.15$8.00
756DeepSeek V3.2 Thinking1144±416.9K1.3%9.0%30 tps2.6s131K$0.28$0.42
865Mistral Large 31133±410.8K2.6%2.1%51 tps1.0s256K$0.50$1.50
986Qwen3 235B A22B1129±37.8K2.1%5.3%71 tps0.9s41K$0.23$0.63
1065DeepSeek V3.2 Exp Chat1125±311.5K1.9%2.6%29 tps1.5s131K$0.27$0.39
1186Nemotron 3 Nano (Thinking)1123±35.9K1.5%2.0%200 tps0.5s256K$0$0
1252Qwen3.5 122B A17B1123±52.6K1.3%1.5%82 tps1.4s256K$0.40$3.20
1395DeepSeek-R1 Turbo1104±54.8K1.5%2.6%29 tps1.8s64K$2.85$4.75
14133Qwen3 14B1088±48.2K2.3%1.7%109 tps0.8s41K$0.04$0.15
1595DeepSeek V3.2 Exp Thinking1084±54.8K1.9%7.2%26 tps3.0s131K$0.28$0.42
16101gpt-oss-20b1080±214.2K1.7%0.5%216 tps0.5s131K$0.06$0.26
17106DeepSeek V3.1 Terminus Thinking1075±46.7K1.9%5.9%27 tps1.8s131K$0.56$1.68
18161DeepSeek Prover v21075±101.4K1.4%5.2%14 tps1.3s164K$0.40$1.56
19126Qwen3 30B A3B1073±49.6K2.1%5.1%163 tps1.0s41K$0.06$0.21
2022MiniMax M2.7-highspeed1071±116752.2%2.3%50 tps2.1s205K$0.60$2.40
21133DeepSeek-R1 05281070±64.4K1.6%1.3%93 tps0.5s64K$1.60$3.67
22113Kimi K2 Fast1067±294.2K1.2%0.8%365 tps0.5s131K$1.00$3.00
23148DeepSeek-R11067±54.9K1.4%0.8%133 tps0.6s64K$0.91$3.07
2481Qwen3.5 27B1065±131.2K2.4%3.7%55 tps2.6s256K$0.30$2.40
2579MiniMax M2.5 Lightning1060±54.1K1.5%1.5%51 tps2.0s205K$0.60$2.40
26121Qwen3 32B Fast1060±411.4K2.3%11.6%30 tps3.1s41K$0.10$0.25
27121QwQ 32B1058±315.3K2.1%5.4%41 tps2.1s16K$0.43$0.56
28129Command A1030±267.4K1.3%2.2%42 tps0.8s256K$2.00$7.33
29126DeepSeek V31027±241.8K1.0%0.9%69 tps1.1s64K$0.59$1.49
30165Qwen3 VL 30B A3B Thinking1027±72.3K4.6%4.5%84 tps2.9s127K$0.20$1.47
31139Qwen3 VL 30B A3B Instruct1009±91.2K4.5%1.8%80 tps2.6s129K$0.18$0.67
32153Qwen 2.5 32B Instruct1005±315.7K1.0%2.5%48 tps1.0s131K$0.21$0.25
33161Mistral Small 3.11005±39.4K1.0%7.4%13 tps2.6s32K$0.17$0.28
34165Pixtral Large997±57.6K1.8%2.5%57 tps1.3s128K$1.50$4.50
35186Gemma 3 27B990±63.1K1.8%1.8%35 tps1.1s66K$0.06$0.10
36170Llama 3.1 8B Turbo989±57.3K1.5%2.1%650 tps0.5s128K$0.13$0.14
37161Llama 4 Maverick987±259.4K1.5%1.2%88 tps2.4s1M$0.23$0.83
38246DeepSeek-R1 Distill Llama 70B973±112.1K3.0%3.6%27 tps1.6s32K$0.73$0.95
39179Llama 3.1 70B Instruct969±158451.7%6.3%30 tps0.8s128K$0.17$0.22
40177Mistral Small 3.1 24B Instruct962±410.6K1.3%7.5%15 tps2.4s131K$0.06$0.18
41194Mistral Small 3 24B Instruct955±47.2K0.9%2.6%77 tps0.6s33K$0.07$0.14
42194Llama 3.2 11B Instruct955±49.2K1.0%1.5%152 tps0.5s8K$0.16$0.16
43201Qwen 2.5 7B Turbo944±92.4K1.5%0.5%125 tps0.4s131K$0.30$0.30
44186GLM 4.6V Flash937±45.8K2.0%3.7%64 tps2.1s128K$0.04$0.40
45201Mistral Small 24B Instruct935±46.3K1.2%1.5%84 tps0.4s33K$0.80$0.80
46194Llama 3 70B934±71.7K1.1%4.5%21 tps1.7s8K$1.08$1.38
47214C4AI Aya Expanse 32B931±317.1K0.8%1.5%43 tps0.5s128K$0.50$1.50
48225Command R 7B928±312.7K1.1%1.1%76 tps0.4s128K$0.04$0.15
49201Gemma 3 27B IT927±38.9K0.9%2.0%60 tps0.8s128K$0.17$0.29
50214Qwen 2.5 7B924±46.9K1.4%3.7%40 tps1.9s131K$0.08$0.27
51214Llama 3.3 70B Instruct Turbo919±83.7K1.5%2.0%78 tps1.0s131K$0.88$0.88
52225Command R913±39.6K1.5%5.8%54 tps0.6s128K$0.30$0.99
53225Open Mistral Nemo910±56.7K1.1%1.5%171 tps0.5s131K$0.15$0.15
54240Mistral Nemo910±53.8K0.5%<0.1%112 tps0.4s131K$0.07$0.13
55235Gemma 3 4B909±411.3K1.0%1.3%138 tps0.7s131K$0.02$0.04
56235Hermes 2 Pro Llama 3 8B908±38.3K0.7%<0.1%76 tps1.0s131K$0.08$0.09
57222Sky T1 32B Preview905±410.5K1.1%7.8%73 tps0.6s16K$0.12$0.18
58229Ministral 8B905±46.8K1.4%1.4%177 tps0.4s128K$0.14$0.14
59235Command R+904±56.3K1.3%2.8%36 tps0.7s128K$2.08$9.45
60235Mixtral 8x7B899±64.7K1.3%2.2%142 tps0.6s33K$0.23$0.23
61256Gemma 3 1B892±56.1K1.9%0.6%176 tps1.0s33K$0.06$0.10
62253Gemma 2 27B889±46.5K1.2%1.4%44 tps1.4s8K$0.80$0.80
63246Ministral 3B886±57.5K1.4%0.8%248 tps0.4s131K$0.08$0.08
64246Mixtral 8x22B Instruct871±45.4K1.6%1.8%142 tps0.7s66K$0.45$0.45
65229Llama 3.1 8B868±91.2K2.4%1.9%61 tps1.0s8K$0.07$0.09
66256Phi 4867±37.7K1.2%5.1%28 tps1.3s128K$0.10$0.32
67260Mistral Small859±64.4K1.6%1.7%142 tps0.6s32K$0.43$1.30
68265Mixtral-8x7B Instruct v0.1849±55K1.5%1.3%54 tps0.4s33K$0.60$0.60
69256Mixtral 8x7B Instruct844±55.7K1.3%0.2%79 tps0.7s33K$0.23$0.31
70240Llama 3.3 70B Instruct839±186752.2%5.3%28 tps1.3s128K$0.38$0.55
71260Hermes 4 405B Reasoning FP8826±45K3.5%3.6%32 tps0.8s131K$1.00$3.00
72271Hermes 3 405B Instruct814±45.5K1.2%2.3%20 tps1.1s131K$0.80$0.80
73281MythoMax L2 13B796±49K1.6%1.2%22 tps1.1s4K$0.18$0.18
74281Gemma 2 9B779±71.3K3.6%<0.1%100 tps0.4s8K$0.09$0.09
75285Phi 4 Mini Instruct774±53.7K2.0%7.4%40 tps1.1s128K$0.07$0.30
76274Pixtral 12B748±152.3K5.1%2.2%101 tps1.2s131K$0.08$0.08
77281Goliath 120B741±92.6K2.1%2.7%21 tps2.2s6K$6.56$9.38
78287Phi 4 Reasoning707±101K2.8%21.0%29 tps1.0s33K$0.06$0.25
79291Phi 4 Mini Reasoning626±84.4K4.9%9.7%30 tps0.9s128K$0.07$0.30
80288Qwen 2.5 VL 3B Instruct624±172.2K7.8%3.0%44 tps2.5s128K$0.21$0.63
Show Less