Reasoning

AIMistral Small 4 is a 119B-parameter MoE model with 6.5B active per token and a 256k context window, combining instruct, reasoning, and Devstral-style coding in one model.

Why it matters: The model card names concrete architecture, context, and licensing details, letting readers compare its reasoning toggle and efficiency claims against other open models.

AIZ.ai has released GLM-4.7-Flash, a 30B-A3B MoE model that it positions as the strongest model in the 30B class. The model reports SWE-bench Verified 59.2 and τ²-Bench 79.5, and supports local deployment through vLLM and SGLang.

Why it matters: The source lists benchmark scores against Qwen3-30B-A3B-Thinking-2507 and GPT-OSS-20B, letting readers compare the 30B-class MoE model directly with its named rivals.

AIAndrej Karpathy's year-in-review lists the LLM paradigm changes he found most notable in 2025.

Why it matters: Karpathy ties the year's shifts to RLVR, jagged capability, and local agents, giving readers a framework for judging how LLM progress is changing.

AIXiaomi released and open-sourced MiMo-V2-Flash, a Mixture-of-Experts model with 309B total and 15B active parameters, under the MIT license.

Why it matters: The post gives architecture, speculative decoding speedup, and pricing figures, which help readers judge how the efficiency claims are achieved and what they cost.

AIOpenAI is introducing GPT-5.2 in ChatGPT, describing it as its most advanced model series for professional work.

Why it matters: The post links the model's professional-work focus to GDPval results across 44 occupations, showing how the claimed capability was measured.

AIARC Prize reports that the top Kaggle entry reached 24% on the ARC-AGI-2 private dataset at $0.20 per task, and that all winning solutions and papers are open source.

Why it matters: The post links 2025 competition results to a broader argument about refinement loops, showing how benchmark outcomes are being read as evidence of AI reasoning progress.

AIGoogle's Gemini 3 Deep Think mode is now available in the Gemini app for Ultra users.

Why it matters: The post names the access tier and the coding and scientific task focus, which helps readers judge whether the mode fits their work.

AIQuoc Le, who posts for Google and Gemini, says Gemini 3 Deep Think is now powered by an even stronger version of the engine behind Google's gold medal-level results at IMO and ICPC. He calls it state of the art above state of the art and says more will follow soon.

Why it matters: The post links Deep Think to earlier IMO and ICPC gold-level results and shows benchmark charts, helping readers compare it with Gemini 3 Pro and rival models.

AIMoonshot AI released Kimi K2 Thinking, an open-source thinking model that interleaves step-by-step reasoning with tool calls across 200 to 300 sequential invocations.

Why it matters: The model card gives benchmark tables, quantization details, and deployment settings, letting readers compare Kimi K2 Thinking against GPT-5 and other models on specific tasks.

AIThinking Machines Lab describes on-policy distillation, which samples rollouts from a student model and has a teacher grade each token with reverse KL. The authors report that this matches Qwen3-style reasoning results at a fraction of RL's cost, with AIME'24 reaching 70% in about 150 steps from a 400k SFT checkpoint.

Why it matters: The post explains why on-policy distillation gives dense per-token feedback, letting a small model match RL results at much lower compute cost.

AICognition tested OpenAI's o1-mini and o1-preview in a simplified Devin-Base agent, comparing them with GPT-4o on its internal cognition-golden benchmark.

Why it matters: The post explains how Cognition evaluates coding agents with autonomous, environment-based tests, which shows how base-model swaps are measured in practice.