Benchmarked models

GPT-5.6 Sol tier — OpenAI flagship, run via local codex CLI with ChatGPT account auth.

7/9 done

GPT-5.6 Terra tier — mid-range, run via local codex CLI with ChatGPT account auth.

7/9 done

GPT-5.6 Luna tier — lightweight/cheap, run via local codex CLI with ChatGPT account auth.

7/9 done

Open-weight 21B MoE released under Apache 2.0 with 3.6B active parameters per forward pass.

7/9 done

DeepSeek V4 Flash free tier, run headlessly via the local opencode CLI (`opencode run -m opencode/deepseek-v4-flash-free`) — the same CLI this report is authored with.

7/9 done

Open frontier reasoning and orchestration MoE on a hybrid Transformer-Mamba architecture.

7/9 done

120B-parameter open hybrid MoE that activates 12B per token for complex multi-agent work.

7/9 done

Small, compute-efficient MoE for building specialized agentic AI systems.

7/9 done

Open multimodal 30B-A3B model designed as a perception and context sub-agent.

7/9 done

12B open multimodal reasoning model for video understanding and document intelligence.

8/9 done

9B dense LLM trained from scratch as a unified model for reasoning and non-reasoning tasks.

7/9 done

Cohere’s first agentic coding model, optimized for code generation and repo-level work.

7/9 done

Google DeepMind instruction-tuned MoE with near-31B quality while activating only 3.8B per token.

7/9 done

Google DeepMind 30.7B dense multimodal model with 256K context and configurable thinking mode.

3/9 done

MoE from inclusionAI for responsive agents, instruction following, and multi-turn conversation.

7/9 done

Latest Poolside coding agent model, scoring 70.2% on Terminal-Bench 2.1.

7/9 done

33B-A3B coding agent model from Poolside, a step forward from Laguna XS.2.

7/9 done