google/gemma-4-31B-it
Image-Text-to-Text • 33B • Updated • 287k • • 758
Mike Ravkine PRO
mike-ravkine
AI & ML interests
LLM Research / Development / Evaluation
Recent Activity
liked a model 1 day ago
google/gemma-4-31B-it liked a model 2 days ago
Jackrong/Qwopus3.5-9B-v3 upvoted an article 4 days ago
How I contributed a new model to the Transformers library using CodexOrganizations
liked a
model 1 day ago
liked a
model 2 days ago
upvoted an article 4 days ago
Article
How I contributed a new model to the Transformers library using Codex
•
39
liked a
model 8 days ago
upvoted a paper 9 days ago
liked a
model 11 days ago
liked a
model 16 days ago
liked a
model 18 days ago
liked a
model 23 days ago
liked a
model 26 days ago
liked a
model 27 days ago
liked a
model 28 days ago
posted an update about 1 month ago
Post
287
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 Qwen/Qwen3.5-27B and the large-MoE Qwen/Qwen3.5-122B-A10B-FP8.
The old king is dead - long live the new king 👑
Note that these rankings are based on
With the release of Qwen-3.5 the king has been dethroned by not one but 2 models the mid-dense Qwen/Qwen3.5-27B and the large-MoE 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). liked a
model about 1 month ago
liked 2
models about 2 months ago
upvoted an article 2 months ago
Article
We Got Claude to Build CUDA Kernels and teach open models!
- +2
•
152
liked 3
models 2 months ago
