Hybrid Reasoning With Internal Deliberation

via “extended-reasoning-with-internal-thinking”

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Unique: Implements internalized thinking as part of the inference architecture rather than exposing chain-of-thought tokens, allowing the model to reason without token overhead while maintaining response quality. Uses adaptive computation allocation to balance reasoning depth with response latency based on problem complexity.

vs others: Provides reasoning benefits of extended chain-of-thought without the token cost and latency of explicit reasoning tokens, differentiating it from models like o1 that expose reasoning in the output stream.

via “hybrid-reasoning-with-internal-deliberation”

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

Unique: Built on Llama-3.1-405B with learned routing that selectively activates internal deliberation pathways, allowing the model to choose reasoning depth per query rather than applying uniform extended thinking to all inputs. This contrasts with fixed-depth reasoning models like o1 that always use extended thinking.

vs others: Offers reasoning capabilities with adaptive compute allocation, reducing latency for simple queries compared to models with mandatory extended thinking, while maintaining deep reasoning for complex problems.

via “hybrid-reasoning-mode-switching”

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...

Unique: Implements learned gating mechanism for automatic reasoning mode selection rather than fixed routing rules or user-specified flags, enabling the model to discover optimal reasoning allocation patterns during training on diverse task distributions

vs others: More efficient than standard chain-of-thought models (which always reason) and more capable than fast-only models (which never reason) by learning when reasoning is actually necessary

via “hybrid-reasoning-with-explicit-thinking-mode”

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Unique: Implements user-controlled explicit thinking via prompt templates rather than always-on reasoning, allowing per-request cost-performance optimization. The 37B active parameter subset processes thinking tokens in a separate phase before final generation, unlike models that interleave reasoning throughout decoding.

vs others: Offers finer-grained reasoning control than OpenAI o1 (which always reasons) and better cost efficiency than Claude 3.5 Sonnet's extended thinking by letting developers opt-in only when needed.

via “chain-of-thought reasoning with visible inference tokens”

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

Unique: Open-sourced reasoning tokens with full visibility into intermediate steps, trained via RLHF to learn when deep reasoning is necessary, contrasting with proprietary o1 models that hide reasoning behind a black box. The 37B active parameters enable efficient inference while maintaining reasoning quality through mixture-of-experts or sparse activation patterns.

vs others: Provides equivalent reasoning performance to OpenAI o1 at lower cost while exposing the full reasoning process for auditability, versus o1's hidden reasoning which prevents inspection but may be faster for simple queries.