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.

762
Open Mistral 7B
759
Hermes 4 405B Reasoning FP8
756
DeepSeek-R1 Distill Qwen 14B
754
Goliath 120B
751
Seed Coder 8B Instruct
746
Qwen 2.5 VL 72B Instruct
742
Gemma 3 4B
738
Mixtral 8x22B Instruct
738
Command R+
737
Inflection 3 Productivity
734
Command
734
Meridian
730
Zenith
725
Mistral Nemo 12B Celeste V1.9
722
Pixtral 12B

Last updated about 1 month ago

RankOverallNameVIBE
Score
Confidence
Interval
VotesDownvote %Abort %SpeedLatencyContextCost
(Input)
Cost
(Output)
361262Open Mistral 7B762±181.3K4.7%0.7%176 tps0.4s33K$0.25$0.25
362262Hermes 4 405B Reasoning FP8759±112.7K12.8%3.6%32 tps0.8s131K$1.00$3.00
363361DeepSeek-R1 Distill Qwen 14B756±161.9K6.3%<0.1%44 tps1.7s64K$0.63$0.63
364262Goliath 120B754±247455.7%2.7%21 tps2.2s6K$6.56$9.38
365361Seed Coder 8B Instruct751±226052.4%<0.1%35 tpsN/A32K$0.99$0.99
366262Qwen 2.5 VL 72B Instruct746±202.1K6.0%5.3%25 tps3.7s128K$1.01$2.79
367269Gemma 3 4B742±103.3K4.7%1.3%138 tps0.7s131K$0.02$0.04
368269Mixtral 8x22B Instruct738±171.4K5.6%1.8%142 tps0.7s66K$0.45$0.45
369269Command R+738±151.6K5.6%2.8%36 tps0.7s128K$2.08$9.45
370269Inflection 3 Productivity737±241.5K5.0%0.6%50 tps3.2s8K$2.50$10.00
371361Command734±187654.4%<0.1%25 tpsN/A4K$0.83$1.33
372361Meridian734±399659.8%<0.1%92 tps1.2s131K$0$0
373361Zenith730±288509.6%<0.1%36 tps1.8s131K$0$0
374374Mistral Nemo 12B Celeste V1.9725±181.1K3.5%<0.1%6 tps10.2s8K$0.80$1.20
375269Pixtral 12B722±213K6.3%2.2%101 tps1.2s131K$0.08$0.08
376374Solar Pro 250422720±195306.2%<0.1%13 tps0.6s33K$0$0
377269Inflection 3 Pi719±181.5K4.1%1.1%33 tps3.4s8K$2.50$10.00
378374Mythalion 13B709±101.1K1.3%<0.1%63 tps0.5s4K$0.56$1.13
379269DeepHermes 3 Mistral 24B Preview706±307155.9%2.5%50 tps1.0s33K$0.06$0.25
380276Hermes 3 405B Instruct702±201.4K4.1%2.3%20 tps1.1s131K$0.80$0.80
381374Dolphin 3.0 R1 Mistral 24B701±168907.8%<0.1%13 tps0.1s33K$0.03$0.09
382374Phi 4 Multimodal Instruct697±162.1K6.8%<0.1%17 tps1.4s128K$0.03$0.05
383276DeepSeek-R1 Distill Qwen 32B696±202K5.5%6.2%22 tps1.8s131K$0.37$0.39
384383ArliAI QwQ 32B Arliai RpR V1686±406359.3%<0.1%34 tps1.8s33K$0.02$0.07
385276MiniMax M1686±133.8K5.3%<0.1%31 tps2.8s1M$0.55$2.20
386386MiMo 7B RL655±131.2K3.5%<0.1%31 tps0.4s32K$0.49$0.49
387386Dolphin 2.9.2 Mixtral 8x22B652±191.1K2.6%<0.1%20 tps1.5s16K$0.90$0.90
388386DeepSeek-R1 Distill Qwen 7B633±195655.0%<0.1%0 tpsN/A131K$0.05$0.10
389386Shisa V2 Llama 3.3 70B623±245859.3%<0.1%8 tps2.0s33K$0.03$0.09
390279UI-TARS 1.5 7B610±4053011.7%4.0%75 tps0.9s128K$0.10$0.20
391390ERNIE 4.5 0.3B602±4068511.0%<0.1%85 tps2.2s120K$0$0
392390Llema 7B601±218504.5%<0.1%1 tps15.0s4K$0.80$1.20
393279MythoMax L2 13B600±212.3K5.8%1.2%22 tps1.1s4K$0.18$0.18
394279Phi 4 Mini Instruct599±211K7.1%7.4%40 tps1.1s128K$0.07$0.30
395390DeepSeek-R1 Distill Llama 8B595±191.2K5.6%<0.1%17 tpsN/A32K$0.04$0.04
396279Hunyuan A13B Instruct588±221.6K9.2%2.3%67 tps2.0s33K$0.01$0.01
397279Phi 4 Reasoning573±172.1K5.5%21.0%29 tps1.0s33K$0.06$0.25
398284Qwen 2.5 VL 3B Instruct523±254.1K6.1%3.0%44 tps2.5s128K$0.21$0.63
399399DeepSeek-R1 Distill Qwen 1.5B481±197305.2%<0.1%20 tps0.0s131K$0.18$0.18
400284CodeLlama 7B Instruct Solidity463±544858.5%3.6%33 tps0.7s16K$0.80$1.20
View All (404 models)