kuku-content-checks · Models

Which model should Dvar use to score your traffic?

The judge, topic names, rubric drafts and alternative replies call these models with your tested key, through the Dvar connector.

Only a member adds a key.

Model
Choose per step A different model for a step, on the same key.
Judge
Topic names
Rubric drafts
Alternative reply

Only a member picks the models.

Models on Dvar Inference

Open-weight models served from India. Tested ones show their share of benchmark messages fully right; the judge that scores replies is openai/gpt-6-sol.

ModelPrice per 1M tokens (in / out)On this benchmark
DeepSeek V4 Flash dvar:deepseek-v4-flash-0731₹10 / ₹20not tested
Gemma 4 26B dvar:gemma-4-26b-a4b-it₹10 / ₹30not tested
Gemma 4 31B dvar:gemma-4-31b-it₹10 / ₹30wrote the synthetic messages
GLM 5.3 dvar:glm-5.3₹105 / ₹340not tested
GLM 5.3 Flash dvar:glm-5.3-flash₹10 / ₹4080.0% fully right
gpt-oss-120b dvar:gpt-oss-120b₹10 / ₹40not tested
Muse Glimmer 30B dvar:muse-glimmer-30b₹25 / ₹110not tested
Nemotron 3.5 30B dvar:nemotron-3.5-lightning-30b-a3b-bf16₹5 / ₹20not tested
Qwen 3.8 27B dvar:qwen-3.8-27b-fp8₹25 / ₹210not tested
——