Tag
reasoning-models
11 articles
GRPO: The Critic-Free RL Algorithm Behind DeepSeek-R1
GRPO (Group Relative Policy Optimization) is a critic-free reinforcement learning algorithm introduced in the DeepSeekMath paper (arXiv 2402.03300). Instead of training a separate value model like PPO, it samples a group of responses per prompt and computes each response's advantage relative to the group's mean and standard deviation. It powered DeepSeek-R1's emergent reasoning and is the central baseline for reinforcement learning with verifiable rewards in 2026, spawning variants like Dr. GRPO, DAPO, and GSPO.
By Aisha Patel · 6 min · Jul 22, 2026
Grok 4.5: xAI's Opus-Class Coder at a Third of the Price
Grok 4.5, released July 8, 2026, is xAI's coding-focused model. It ranks 4th on the Artificial Analysis Intelligence Index (score 54), wins SWE Marathon (29%), and prices at $2/$6 per million tokens with 4.2x better token efficiency than Opus 4.8. Not yet available in the EU.
By Sarah Chen · 5 min · Jul 12, 2026
GPT-Realtime-2.1: OpenAI Adds Reasoning to Its Voice API
On July 6, 2026, OpenAI released GPT-Realtime-2.1 and GPT-Realtime-2.1-mini for the Realtime API. The headline change is reasoning in the low-cost mini tier, plus a 25% cut in p95 latency from better caching. The mini holds the prior gpt-realtime-mini price (0 audio in, 0 audio out per 1M) while the full model runs 2/4. Reasoning effort is configurable from minimal to xhigh.
By Sarah Chen · 5 min · Jul 8, 2026
GPT-5.6 Sol: OpenAI's Best Model, Held Back by Washington
On June 26, 2026, OpenAI previewed the GPT-5.6 series — Sol (flagship), Terra (balanced, 2x cheaper than GPT-5.5), and Luna (fastest, cheapest) — but restricted access to trusted partners at the US government's request due to the models' strong cybersecurity capabilities. OpenAI paired the release with its most robust layered safeguard stack and said it does not want government pre-release review to become the default.
By Sarah Chen · 6 min · Jul 2, 2026
Claude Sonnet 5: Anthropic's Most Agentic Mid-Tier Model Yet
Claude Sonnet 5, released June 30, 2026, is Anthropic's most agentic mid-tier model. It beats Sonnet 4.6 on every published benchmark (63.2% SWE-bench Pro, 80.4% Terminal-Bench 2.1, 81.2% OSWorld) and edges Opus 4.8 on GDPval-AA v2 knowledge work. Intro pricing is /0 per million tokens through Aug 31, 2026, then /5. A new tokenizer can raise token counts up to 1.35x, and xhigh effort can cost more than Opus 4.8.
By Sarah Chen · 5 min · Jul 1, 2026
MAI-Thinking-1: Microsoft's First In-House Reasoning Model
Microsoft unveiled MAI-Thinking-1 at Build 2026, its first reasoning model trained in-house without distillation. The 35B-active, ~1T-total MoE has a 256k context window, scores 97.0% on AIME 2025 and matches Claude Opus 4.6 on SWE-Bench Pro. It's in private preview on Microsoft Foundry.
By Sarah Chen · 5 min · Jun 23, 2026
Test-Time Compute: Why Reasoning Models Think Before Answering
Test-time compute spends extra computation during inference, not training, to improve answers. It powers reasoning models like OpenAI o1 and DeepSeek-R1. Two strategies exist: sequential scaling (longer chains of thought, e.g. the s1 paper's budget forcing) and parallel scaling (Best-of-N, majority voting). More thinking is not always better, overthinking degrades accuracy, and hidden reasoning tokens are billable. Match compute to task difficulty.
By Aisha Patel · 8 min · Jun 17, 2026
Diffusion LLMs: How Text Diffusion Is Challenging Autoregression
Diffusion language models (dLLMs) abandon left-to-right autoregressive generation, instead refining masked noise into text over a few parallel denoising steps. Inception Labs' Mercury Coder runs at 1,100+ tokens per second on H100s versus 50-200 for autoregressive models, and LLaDA 8B's bidirectional design breaks the reversal curse. They still trail the best models on hard reasoning benchmarks, but the one-token-at-a-time assumption is no longer a law of nature.
By Aisha Patel · 8 min · Jun 12, 2026
ZAYA1-8B: Zyphra's 760M-Active MoE Trained on AMD
Zyphra's ZAYA1-8B MoE model, trained on AMD, achieves high performance with efficient parameter activation.
By Aisha Patel · 6 min · May 24, 2026
Trinity-Large-Thinking: 400B U.S.-Made Open Reasoning Model
Trinity-Large-Thinking is Arcee AI's 400B open-weights reasoning model, offering powerful, cost-effective agent tuning.
By Aisha Patel · 7 min · Apr 30, 2026
DeepSeek V4 Pro: 1.6T Open-Weights Model Hits #2 on the Index
DeepSeek V4 Pro is a top 1.6T open-weights model for agents, but has a high hallucination rate.
By Sarah Chen · 5 min · Apr 29, 2026