mike-ravkine/GLM-4.7-REAP-50-FP8-Dynamic
Text Generation • 185B • Updated
• 10
Mike Ravkine PRO
mike-ravkine
AI & ML interests
LLM Research / Development / Evaluation
Recent Activity
liked
a model about 2 hours ago
LLM360/K2-Think-V2 liked
a model 1 day ago
inclusionAI/Ring-flash-2.0 posted an
update
4 days ago
gpt-oss-120b has held on to the ReasonScape crown since it's release on Aug 5, 2025 - 7 months in the LLM space is *impressive*.
With the release of Qwen-3.5 the king has been dethroned by not one but 2 models the mid-dense https://huggingface.co/Qwen/Qwen3.5-27B and the large-MoE https://huggingface.co/Qwen/Qwen3.5-122B-A10B-FP8.
The old king is dead - long live the new king 👑
Note that these rankings are based on `r12` - a 27k prompts, 12 task domain 3rd iteration of the ReasonScape evaluation. Compared to the previous m12x ranking this evaluation fixes a slew of test bugs, refines the task set to add table-extraction, and lifts the context ceiling to 16k - so these rankings are quite a bit different vs the previous m12x Leaderboard (which has an 8k context limit). Organizations
