Modelpublic

OrionLLM/GRM-2.6-Plus-0628

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

36likes132downloads

Model Card

1. Introduction

GRM-2.6-Plus-0628 is a 27B-parameter reasoning model and a small update to GRM-2.6-Plus, built for general-purpose AI and optimized for difficult, high-complexity tasks. It is designed to deliver stronger performance for its size while remaining practical, efficient, and accessible for advanced local and research-oriented use.

This version improves upon GRM-2.6-Plus with a focus on long-horizon agentic tasks and the ability to solve harder problems, allowing it to better compete head-to-head with frontier models. The model focuses on structured reasoning, helping it produce more accurate, coherent, and reliable responses across demanding problems. GRM-2.6-Plus-0628 brings elite-level reasoning to complex workloads, making it suitable for users who need a capable model for advanced problem-solving, coding, agents, and everyday intelligence.

2. Key Capabilities

—Elite-Level Reasoning for Hard Tasks: GRM-2.6-Plus-0628 is optimized to handle difficult reasoning workloads with clarity, consistency, and strong step-by-step problem-solving ability.
—Improved Long-Horizon Agentic Performance: This update specifically targets long-horizon agentic workflows, enabling the model to maintain coherence and effectiveness across extended multi-step tasks.
—High Performance for Its Size: With 27B parameters, the model is designed to deliver excellent capability relative to its scale, balancing strong intelligence with practical deployment.
—Advanced Coding and Agentic Use: GRM-2.6-Plus-0628 is well suited for code generation, structured problem-solving, tool-style workflows, and local agentic applications.
—Optimized for Practical Deployment: The model aims to remain efficient and usable across capable consumer and workstation hardware while offering strong performance for advanced tasks.

[!Important] 2026-07-27 Update — Chat template fix (tool calls inside reasoning), v2. Fixes tool calls landing in reasoning_content instead of tool_calls on llama.cpp and other engines that rely on the template's forced-open <think> prefill. (1) Explicit close directive: the <IMPORTANT> block now requires </think> to be closed in every response, unconditionally, with no conversational text before the tool call. (2) Closing-tag variant detection: the history parser now recognizes </think>, </thinking>, and common malformed variants (</ think>, </think >), not just the exact tag — borrowed from community testing on the wider Qwen3.5/3.6 template ecosystem. (3) Empty-think guard: past turns with no actual reasoning content no longer render an empty <think>\n\n</think> block. Empty-think injection was training the model, in-context, to associate "no thinking" with "tool call," which made the bug worse over multi-turn agentic loops. (4) History parse fallback: assistant turns that contain <tool_call> but no closing think tag are split at the tool-call boundary instead of dumping the raw XML as plain text into content. (5) `auto_disable_thinking_with_tools` kwarg (optional, default `false`): scoped to individual turns that follow a tool_response, not session-wide — so planned next-steps in an agentic loop skip the forced <think> block, while turns that genuinely need extended reasoning keep it. No action needed beyond replacing chat_template.jinja. Upstream tracking: ggml-org/llama.cpp#22684, #20260.

3. Performance

GRM-2.6-Plus-0628 is designed to be a highly capable 27B local AI model for complex reasoning, coding, everyday chat, and agentic workflows. It focuses on delivering better performance for its size, making it a strong option for users who want powerful reasoning without relying only on massive-scale models.

Its core strength is practical intelligence: elite-level reasoning, strong task understanding, stable responses, and the ability to handle difficult problems across multiple domains.

Detailed Benchmarks

<table> <tr> <th style="background: rgba(128,128,128,0.1); text-align: center;"> </th> <th style="background: rgba(128,128,128,0.1); text-align: center;">GRM-2.6-Plus-0628</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">GRM-2.6-Plus</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">Qwen3.6-27B</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">google/gemma-4-31B-it</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">GPT-5.4-Mini</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">Claude-4.5-Haiku</th> </tr> <tr> <td align="center" colspan="7" style="background: linear-gradient(90deg, rgba(124,58,237,0.45) 0%, rgba(99,102,241,0.42) 50%, rgba(59,130,246,0.45) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Knowledge & STEM</i></td> </tr> <tr> <td align="center">MMLU-Pro</td> <td align="center"><b>88.1</b></td> <td align="center">86.8</td> <td align="center">86.2</td> <td align="center">85.2</td> <td align="center">--</td> <td align="center">80.0</td> </tr> <tr> <td align="center">MMLU-Redux</td> <td align="center"><b>96.4</b></td> <td align="center">94.2</td> <td align="center">93.5</td> <td align="center">93.7</td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center">C-Eval</td> <td align="center"><b>92.4</b></td> <td align="center">92.0</td> <td align="center">91.4</td> <td align="center">82.6</td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center">GPQA Diamond</td> <td align="center"><b>90.1</b></td> <td align="center">88.3</td> <td align="center">87.8</td> <td align="center">84.3</td> <td align="center">88.0</td> <td align="center">73.0</td> </tr> <tr> <td align="center">SuperGPQA</td> <td align="center"><b>67.5</b></td> <td align="center">66.4</td> <td align="center">66.0</td> <td align="center">65.7</td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center" colspan="7" style="background: linear-gradient(90deg, rgba(124,58,237,0.45) 0%, rgba(99,102,241,0.42) 50%, rgba(59,130,246,0.45) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Reasoning & Coding</i></td> </tr> <tr> <td align="center">LiveCodeBench v6</td> <td align="center"><b>86.5</b></td> <td align="center">84.8</td> <td align="center">83.9</td> <td align="center">80.0</td> <td align="center">--</td> <td align="center">51.1</td> </tr> <tr> <td align="center">HMMT Feb 26</td> <td align="center"><b>85.9</b></td> <td align="center">84.8</td> <td align="center">84.3</td> <td align="center">77.2</td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center">AIME26</td> <td align="center"><b>95.6</b></td> <td align="center">95.1</td> <td align="center">94.1</td> <td align="center">89.2</td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center" colspan="7" style="background: linear-gradient(90deg, rgba(124,58,237,0.45) 0%, rgba(99,102,241,0.42) 50%, rgba(59,130,246,0.45) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>General Agent</i></td> </tr> <tr> <td align="center">SWE-bench Verified</td> <td align="center"><b>79.7</b></td> <td align="center">77.7</td> <td align="center">77.2</td> <td align="center">52.0</td> <td align="center">--</td> <td align="center">73.3</td> </tr> <tr> <td align="center">SWE-bench Pro</td> <td align="center"><b>56.1</b></td> <td align="center">54.0</td> <td align="center">53.5</td> <td align="center">35.7</td> <td align="center">54.4</td> <td align="center">--</td> </tr> <tr> <td align="center">Terminal-Bench 2.0</td> <td align="center"><b>62.6</b></td> <td align="center">59.8</td> <td align="center">59.3</td> <td align="center">42.9</td> <td align="center">60.0</td> <td align="center">41.0</td> </tr> </table>

4. Family

The GRM-2.6 family is available in various sizes to suit every case.

<table> <tr> <th style="background: rgba(128,128,128,0.1); text-align: center;">Model</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">Size</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">Domain</th> </tr> <tr> <td align="center">GRM-2.6-Plus-0628</td> <td align="center">27B</td> <td align="center">Updated model for extremely difficult tasks with improved long-horizon agentic performance</td> </tr> <tr> <td align="center">GRM-2.6-Plus</td> <td align="center">27B</td> <td align="center">Powerful model for extremely difficult tasks</td> </tr> <tr> <td align="center">GRM-2.6-Opus</td> <td align="center">27B</td> <td align="center">Merge of GRM-2.6-Plus optimized for difficult terminal and coding tasks</td> </tr> </table>

5. Architecture

GRM-2.6-Plus-0628 is built on the Qwen3.6 architecture and is optimized for complex tasks, agent environments, and everyday chat.

GRM-2.6-Plus-0628 applies the same principle to a stronger, larger foundation, resulting in a model that punches above its weight class on structured reasoning tasks while remaining deployable on consumer hardware.

GRM-2.6-Plus-0628 is developed by [OrionLLM](https://huggingface.co/OrionLLM) and released under the Apache 2.0 License.

</div>