---
license: apache-2.0
base_model:
- deepreinforce-ai/Ornith-1.0-9B
pipeline_tag: image-text-to-text
---
## 1. Introduction
We're introducing **GRM-3.2-Cliff**, our intermediate model built for **long-horizon agentic tasks** and **extremely difficult reasoning problems** in local environments. GRM-3.2-Cliff marks a substantial leap in long-horizon task capability over its predecessor, **GRM-2.5-Plus**, and is designed to serve as a dependable engine for complex, multi-step local workflows.
The model is purpose-built for **long-horizon agentic tasks** and problems that are simply *hard* — difficult coding challenges, advanced mathematics, and rigorous logical reasoning. GRM-3.2-Cliff aims to sustain coherent, goal-directed behavior over extended interactions while remaining optimized for resource-constrained hardware, making it ideal for developers and researchers who need local execution without sacrificing multi-step planning and self-correction performance.
## 2. Key Capabilities
- **Long-Horizon Agentic Mastery:** GRM-3.2-Cliff is specifically optimized to maintain coherence, planning quality, and task fidelity across long, multi-step agentic workflows, representing a major upgrade over GRM-2.5-Plus.
- **Local Workflow Efficiency:** Engineered to run smoothly in lower GPU environments while delivering high-tier reasoning performance.
- **Elite Reasoning on Hard Problems:** Strong performance on difficult coding, advanced mathematics, and logical reasoning tasks with careful, structured step-by-step problem-solving.
- **Robust Coding Ability:** Handles complex, multi-file coding tasks, debugging, refactoring, and long-running terminal sessions locally.
- **Consistent Logical Reasoning:** Built to reason carefully through multi-constraint logic problems without losing track of intermediate steps over extended execution runs.
## 3. Performance
GRM-3.2-Cliff is designed as our premier mid-sized model for local, long-horizon agentic work. It builds directly on the strengths of GRM-2.5-Plus while targeting common edge-case failures in smaller models — contextual drift, multi-step degradation, and loss of initial goal states — delivering strong reliability across extended sessions.
### Detailed Benchmarks
| |
GRM-3.2-Cliff |
GRM-2.5-Plus |
GPT-5.6-Luna |
Sonnet 5 |
Gemini 3 Pro |
| Knowledge & STEM |
| MMLU-Pro |
83.3 |
84.2 |
— |
— |
89.8 |
| GPQA Diamond |
82.4 |
82.7 |
92.3 |
— |
91.9 |
| Reasoning & Coding |
| LiveCodeBench v6 |
69.3 |
67.2 |
— |
— |
82.9 |
| General Agent |
| SWE-bench Verified |
70.3 |
— |
— |
85.2 |
76.2 |
| SWE-bench Pro |
43.4 |
— |
62.7 |
63.2 |
— |
| Terminal-Bench 2.1 |
45.3 |
— |
84.7 |
80.4 |
— |
| NL2Repo |
28.5 |
— |
— |
— |
— |
*Scores are taken from each provider's own published model card, blog post, or system card where available; "—" indicates a score was not publicly reported by that provider at the time of writing. Different labs may use different agent scaffolds when reporting SWE-bench and Terminal-Bench results, so cross-provider comparisons should be read with that caveat.*
## 4. Family
The GRM-3.2 family is available in various sizes to suit every use case.
| Model |
Size |
Domain |
| GRM-3.2-Sky |
35B-A3B |
Flagship model for long-horizon tasks |
| GRM-3.2-Cliff |
9B |
Capable model for low GPU environments |
| GRM-3.2-Turf |
1.2B |
Lightweight model for practical reasoning |
## 5. Architecture
GRM-3.2-Cliff is built on the **Ornith-1.0-9B** architecture, a 9B-parameter model optimized for long-horizon agentic workflows, complex coding tasks, advanced mathematics, and logical reasoning, structured to run efficiently in low-to-mid GPU hardware environments.
---
**GRM-3.2-Cliff** is developed by **[OrionLLM](https://huggingface.co/OrionLLM)** and released under the Apache 2.0 License.
