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.

258
Phi 4 Mini Reasoning
486
Phi 4 Reasoning
565
Refuel LLM 2 Small
647
Claude Haiku 3
654
GPT-4o mini
679
Qwen 2.5 14B Instruct
681
Hermes 4 405B Reasoning FP8
689
Gemma 3 12B
707
MiniMax M1
708
Fauna Fox
709
C4AI Aya Expanse 32B
710
Switchpoint Router
714
DeepSeek-R1 Distill Qwen 14B
724
Gemma 3 4B
726
Llama 3.3 70B

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
1291Phi 4 Mini Reasoning258±229357.0%9.7%30 tps0.9s128K$0.07$0.30
2287Phi 4 Reasoning486±325302.8%21.0%29 tps1.0s33K$0.06$0.25
3339Refuel LLM 2 Small565±275252.8%<0.1%116 tps0.5s8K$0.20$0.20
4241Claude Haiku 3647±425252.8%0.4%62 tps0.5s200K$0.25$1.25
5201GPT-4o mini654±305154.6%2.1%71 tps1.7s128K$0.15$0.60
6209Qwen 2.5 14B Instruct679±225053.8%2.4%40 tps1.6s1M$0.40$1.61
7260Hermes 4 405B Reasoning FP8681±317255.2%3.6%32 tps0.8s131K$1.00$3.00
8214Gemma 3 12B689±235504.3%4.2%73 tps0.8s131K$0.05$0.12
9284MiniMax M1707±141.5K1.0%<0.1%31 tps2.8s1M$0.55$2.20
10182Fauna Fox708±231.1K4.5%<0.1%194 tps0.3s128K$0.04$0.15
11214C4AI Aya Expanse 32B709±229251.6%1.5%43 tps0.5s128K$0.50$1.50
12179Switchpoint Router710±266203.1%1.7%71 tps4.9s131K$0.85$3.40
13406DeepSeek-R1 Distill Qwen 14B714±335702.6%<0.1%44 tps1.7s64K$0.63$0.63
14235Gemma 3 4B724±246603.6%1.3%138 tps0.7s131K$0.02$0.04
15194Llama 3.3 70B726±267355.2%0.3%500 tps0.5s8K$0.48$0.66
16241Arcee AI Blitz728±176550.8%<0.1%6 tpsN/A33K$0.45$0.75
17225Command R730±236052.4%5.8%54 tps0.6s128K$0.30$0.99
18274DeepSeek-R1 Distill Qwen 32B736±225701.7%6.2%22 tps1.8s131K$0.37$0.39
19233Llama 3.1 70B Instruct Turbo739±209003.2%<0.1%110 tps0.8s128K$0.88$0.88
20222Jamba 1.5 Large744±247152.1%1.7%48 tps0.9s256K$1.50$6.00
21177Llama 3 70B Turbo755±141.1K5.1%<0.1%31 tps0.0s8K$0.73$0.83
22246DeepSeek-R1 Distill Llama 70B755±199602.5%3.6%27 tps1.6s32K$0.73$0.95
23186Jamba 1.6 Large761±157801.9%2.0%59 tps1.2s256K$1.33$5.33
24200K2 Think763±246050.8%<0.1%418 tps2.8sN/A$0$0
25270Solar Pro 2 250710 (Reasoning)782±226051.6%<0.1%9 tpsN/A66K$0.50$0.50
26229Magistral Medium 2509782±285507.6%4.0%58 tps0.9s131K$2.00$5.00
27200NVIDIA Llama 3.1 Nemotron 70B783±171.2K2.4%<0.1%9 tps0.1s128K$0.33$0.39
28219Grok 3 Mini Beta783±176050.8%<0.1%75 tps0.5s131K$0.45$2.25
29225Command R 7B787±266602.9%1.1%76 tps0.4s128K$0.04$0.15
30292Arcee AI Spotlight788±151.1K1.3%<0.1%121 tps0.4s131K$0.18$0.18
31270AFM 4.5B Preview797±386103.9%<0.1%32 tps0.0s66K$0$0
32277Grok 2798±185550.9%<0.1%55 tps1.1s131K$2.00$10.00
33179Amazon Nova Pro 1.0803±131.2K2.0%0.9%96 tps0.7s300K$0.80$1.70
34186Grok 3 Mini Fast807±142.4K1.8%1.6%44 tps0.5s131K$0.60$4.00
35186Gemma 3n E4B814±171.6K3.6%2.0%30 tps0.5s8K$0.01$0.02
36235GLM 4 32B820±167002.1%2.6%40 tps1.6s33K$0.14$0.14
37222Sky T1 32B Preview821±186251.6%7.8%73 tps0.6s16K$0.12$0.18
38277Wikipedia821±131.7K5.9%<0.1%47 tps2.1s32K$0$0
39399Magistral Medium (Thinking)822±246001.6%<0.1%67 tps0.8s41K$2.00$5.00
40314MAI-DS-R1823±198554.5%<0.1%73 tps3.2s64K$0.10$0.40
View All (223 models)