# TII — Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling

- Company: TII (tii.ae)
- Announced: 2026-01-05T08:00:00+00:00
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://falcon-lm.github.io/blog/falcon-h1r-7b/
- Record: https://forck.live/items/18412-falcon-h1r-pushing-the-reasoning-frontiers-with-a-hybrid-model-for-efficient
- Subject: Falcon LLM
- Open weights: yes
- Models affected: Falcon H1R 7B, Falcon-H1 Base

TII released Falcon H1R 7B, a decoder-only large language model built on the Falcon-H1 Base. The 7B-parameter model matches or outperforms reasoning models 2–7× larger on math, code, and general benchmarks. Its training uses a two-stage pipeline of supervised fine-tuning and GRPO reinforcement learning, and it employs a Deep Think with Confidence (DeepConf) method for test-time scaling.

## Evidence

Verbatim from https://falcon-lm.github.io/blog/falcon-h1r-7b/:

> Despite its modest 7 billion‑parameter size, Falcon H1R 7B matches or outperforms state‑of‑the‑art reasoning models that are 2–7× larger, proving its exceptional parameter efficiency and does so consistently across a wide range of reasoning‑intensive benchmarks.

---

Record: https://forck.live/items/18412-falcon-h1r-pushing-the-reasoning-frontiers-with-a-hybrid-model-for-efficient
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md