Spaces:

---

DontPlanToEnd

/

UGI-Leaderboard

like 1.25k

Running

I would like to kindly ask to eval the following models:

Finetunes:

• https://huggingface.co/zerofata/GLM-4.5-Iceblink-v2-106B-A12B
• ̶ ̶h̶t̶t̶p̶s̶:̶/̶/̶h̶u̶g̶g̶i̶n̶g̶f̶a̶c̶e̶.̶c̶o̶/̶T̶h̶e̶D̶r̶u̶m̶m̶e̶r̶/̶S̶k̶y̶f̶a̶l̶l̶-̶3̶6̶B̶-̶v̶2̶
• ̶h̶t̶t̶p̶s̶:̶/̶/̶h̶u̶g̶g̶i̶n̶g̶f̶a̶c̶e̶.̶c̶o̶/̶R̶e̶a̶d̶y̶A̶r̶t̶/̶D̶a̶r̶k̶-̶N̶e̶x̶u̶s̶-̶3̶2̶B̶-̶v̶2̶.̶0̶ ̶(hybrid-̶r̶e̶a̶s̶o̶n̶i̶n̶g̶)̶
• ̶h̶t̶t̶p̶s̶:̶/̶/̶h̶u̶g̶g̶i̶n̶g̶f̶a̶c̶e̶.̶c̶o̶/̶E̶w̶e̶r̶e̶/̶Q̶w̶e̶n̶3̶-̶3̶0̶B̶-̶A̶3̶B̶-̶a̶b̶l̶i̶t̶e̶r̶a̶t̶e̶d̶-̶e̶r̶o̶t̶i̶c̶ ̶(̶r̶e̶a̶s̶o̶n̶i̶n̶g̶)̶

REAPed base model:

• https://huggingface.co/cerebras/GLM-4.5-Air-REAP-82B-A12B (hybrid reasoning)
• https://huggingface.co/cerebras/GLM-4.6-REAP-218B-A32B (hybrid reasoning)

Base models:

• https://huggingface.co/aquif-ai/aquif-3.5-Max-42B-A3B (reasoning)
• https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B (hybrid reasoning)
• h̶t̶t̶p̶s̶:̶/̶/̶h̶u̶g̶g̶i̶n̶g̶f̶a̶c̶e̶.̶c̶o̶/̶M̶i̶n̶i̶M̶a̶x̶A̶I̶/̶M̶i̶n̶i̶M̶a̶x̶-̶M̶2̶ ̶(̶r̶e̶a̶s̶o̶n̶i̶n̶g̶)
• ̶h̶t̶t̶p̶s̶:̶/̶/̶h̶u̶g̶g̶i̶n̶g̶f̶a̶c̶e̶.̶c̶o̶/̶m̶o̶o̶n̶s̶h̶o̶t̶a̶i̶/̶K̶i̶m̶i̶-̶K̶2̶-̶T̶h̶i̶n̶k̶i̶n̶g̶ ̶(̶r̶e̶a̶s̶o̶n̶i̶n̶g̶)̶
• ̶h̶t̶t̶p̶s̶:̶/̶/̶h̶u̶g̶g̶i̶n̶g̶f̶a̶c̶e̶.̶c̶o̶/̶n̶v̶i̶d̶i̶a̶/̶Q̶w̶e̶n̶3̶-̶N̶e̶m̶o̶t̶r̶o̶n̶-̶3̶2̶B̶-̶R̶L̶B̶F̶F̶ ̶ ̶(̶r̶e̶a̶s̶o̶n̶i̶n̶g̶)̶

Thank you very much for your amazing work!