Reflection’s Beam is a 501-billion-parameter sparse Mixture-of-Experts model with 23 billion active parameters. Its larger story is efficiency: high-compute reinforcement learning, long tool-using rollouts, and controllable reasoning aim to make coding agents capable without paying dense-model costs on every token.
Artificial Analysis’ Intelligence Index combines multiple reasoning and coding evaluations into a single 0–100 score. Qwen3.8 27B reportedly scored 52, suggesting strong task-completion behavior for a 27B-size model.
Muse Glimmer is Meta’s open-weight 30B agentic model released under Apache 2.0, designed to run locally for coding and tool-using workflows. Its local feasibility comes from quantization for memory fit and DFlash-based speculative decoding for faster generation.
Thinking Machines’ Inkling is an open-weights, multimodal MoE LLM with 975B total parameters and 41B active per token. It supports long context (up to 1M tokens), controllable thinking effort, and fine-tuning via Tinker.