# Ring-1T

> Source: https://aiwiki.ai/wiki/ring_1t
> Updated: 2026-06-09
> Categories: AI Models, Large Language Models, Open Source AI
> From AI Wiki (https://aiwiki.ai), a free encyclopedia of artificial intelligence. Quote with attribution.

**Ring-1T** is an [open-weight](/wiki/open_weights) [reasoning model](/wiki/reasoning_models) released in October 2025 by inclusionAI, the open-source research initiative associated with [Ant Group](/wiki/ant_group), the Alibaba-affiliated financial-technology company that operates the Alipay payments platform. With roughly 1 trillion total parameters and only about 50 billion activated per token through a sparse [mixture-of-experts](/wiki/mixture_of_experts) (MoE) design, Ring-1T was described by its developers and by independent observers as the first open-source, trillion-parameter-scale "thinking" model, making it one of the largest openly released reasoning models at the time.[1][2] It is the reasoning ("thinking") flagship of inclusionAI's paired Ling and Ring model families, both built on a shared "Ling 2.0" architecture.[3]

## Overview

Ring-1T is a chain-of-thought reasoning model: it produces an extended internal deliberation before emitting a final answer, a design pattern popularized by models such as [OpenAI](/wiki/openai)'s o1 and [DeepSeek](/wiki/deepseek)-R1. It is built on the same trillion-parameter foundation as inclusionAI's non-thinking model, [Ling-1T](/wiki/ling_1t), and was further trained with large-scale reinforcement learning to specialize in mathematics, code generation, and logical reasoning.[1][3]

The model was first released as "Ring-1T-preview" on September 30, 2025, with the complete Ring-1T following in mid-October 2025; the accompanying technical report, titled "Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model," was published on arXiv on October 21, 2025.[1][2] Weights were distributed openly on [Hugging Face](/wiki/hugging_face) and ModelScope under the permissive MIT license, including a quantized FP8 variant to ease deployment of the very large model.[2]

## Specifications

| Attribute | Detail |
| --- | --- |
| Developer | inclusionAI (associated with Ant Group) |
| Model family | Ring (thinking) / Ling 2.0 architecture |
| Type | Reasoning ("thinking") large language model |
| Architecture | Sparse mixture-of-experts (MoE) |
| Total parameters | ~1 trillion |
| Activated parameters | ~50 billion per token |
| Base model | Ling-1T-base |
| Context length | Up to 128K tokens |
| Training | Reinforcement learning with verifiable rewards (RLVR) plus RLHF |
| Preview release | September 30, 2025 (Ring-1T-preview) |
| Full release | October 2025 |
| Technical report | arXiv:2510.18855, October 21, 2025 |
| License | MIT |
| Availability | Hugging Face, ModelScope (incl. FP8 quantization) |

## Developer: inclusionAI and Ant Group

inclusionAI is the open-source brand under which Ant Group releases its large language models. Ant Group, formerly Ant Financial, is an Alibaba-affiliated company best known for operating Alipay, one of China's largest digital payment and financial-services platforms. Ant began open-sourcing its Ling MoE models under the inclusionAI umbrella in 2025, positioning itself as a new entrant among China's frontier-model developers alongside [DeepSeek](/wiki/deepseek), [Alibaba](/wiki/alibaba)'s [Qwen](/wiki/qwen) team, and [Moonshot AI](/wiki/moonshot_ai), maker of Kimi.[3][4] The teams behind the models are sometimes referred to internally by the "Bailing" (Ling) name, and the technical report credits a large "Ling Team" of more than a hundred contributors.[1]

## The Ling and Ring families

inclusionAI organizes its models into two parallel lines that share a common foundation. The **Ling** series consists of general-purpose, non-thinking instruction models, while the **Ring** series consists of reasoning ("thinking") models that perform explicit step-by-step deliberation. Both are built on the **Ling 2.0** mixture-of-experts architecture, which inclusionAI began open-sourcing in September 2025 starting with smaller variants such as Ling-mini-2.0 and Ring-mini-2.0.[3][5]

At the top of the range, the non-thinking **Ling-1T** and the thinking **Ring-1T** share the same trillion-parameter MoE backbone: Ling-1T is the flagship instruction model, and Ring-1T is the reasoning model trained on top of the Ling-1T-base foundation.[3] Ling-1T introduced architectural choices intended to stabilize training at trillion scale, including an auxiliary-loss-free, sigmoid-scored expert-routing balance strategy and QK normalization, which Ring-1T inherits.[6] inclusionAI later iterated on the line with updated releases such as the Ling/Ring 2.5 and 2.6 generations in 2026, the latter of which increased activated parameters and extended the context window.[7]

## Architecture and RL training

Ring-1T's sparse MoE design means that although the model contains on the order of 1 trillion parameters in total, only a small fraction, about 50 billion, is activated for any given token. This lets the model approach the capability of a very large dense network while keeping per-token inference cost far lower than its nominal size would suggest. The model supports a context window of up to 128K tokens.[1][2]

The technical report frames Ring-1T primarily as an exercise in scaling reinforcement learning to trillion-parameter models, and it introduces several methods to make that feasible:[1]

- **IcePop** (sometimes styled "Icepop") stabilizes RL training by addressing the discrepancy between the training and inference computation paths in MoE models. The report describes it as using token-level discrepancy masking and clipping (a "masked bidirectional truncation" technique) to suppress instability that would otherwise accumulate over long training runs.[1][2]
- **C3PO++** improves efficiency for long reasoning rollouts by dynamically partitioning them, improving time and resource utilization during generation-heavy RL.[1]
- **ASystem** is a high-performance RL framework built to overcome the systemic engineering bottlenecks of trillion-parameter training. It uses a SingleController plus SPMD design with features such as transparent memory offloading and a high-throughput, sandboxed reward service.[1][2]

Training combined reinforcement learning with verifiable rewards (RLVR), where correctness can be checked automatically for tasks like math and code, with reinforcement learning from human feedback (RLHF) for broader alignment.[2]

## Benchmarks

inclusionAI reported that Ring-1T achieves leading open-source results across math, code, and logical-reasoning benchmarks, and approaches the performance of leading closed (proprietary) systems on several tasks. Reported scores include 93.4 on AIME 2025 and 86.72 on HMMT 2025 (both competition-mathematics benchmarks), a CodeForces rating of 2088, and 55.94 on the abstract-reasoning benchmark ARC-AGI-1.[2][8] The developers also cited strong results on LiveCodeBench, the comprehensive Arena-Hard v2.0 benchmark, the HealthBench medical benchmark, and Creative Writing v3, and positioned Ring-1T against open models such as DeepSeek-V3.1 and Qwen3-235B-A22B-Thinking as well as closed APIs including [Gemini](/wiki/gemini) 2.5 Pro and GPT-5 (Thinking).[1][8]

The most widely cited result is Ring-1T's performance on the 2025 International Mathematical Olympiad (IMO). According to inclusionAI, the model produced correct solutions to problems 1, 3, 4, and 5, reaching a silver-medal-level standard, with a near-complete solution to problem 2; it did not solve problem 6.[1][2] On the 2025 International Collegiate Programming Contest (ICPC) problem set, the model was reported to solve 5 of 11 problems within three attempts.[2] As with all self-reported benchmark figures, these results come from the developer's own evaluation and had not been independently standardized at release; they should be read as the developer's claims rather than neutral measurements.

## Availability and significance

Ring-1T was released as an open-weight model under the MIT license on Hugging Face and ModelScope, with an FP8 quantized version provided to reduce the memory needed to run it.[2] Even so, the model's trillion-parameter scale places it beyond the reach of typical consumer hardware, and it is generally accessed through cloud inference providers or substantial multi-GPU deployments; third-party platforms such as SiliconFlow began hosting it shortly after release.[8]

Ring-1T is significant as one of the first openly released reasoning models at trillion-parameter scale, and as a marker of Ant Group's entry into frontier model development. Its arrival extended a broader 2025 trend of Chinese laboratories releasing very large open-weight MoE systems, alongside DeepSeek's V3 and R1 models, Alibaba's Qwen series, and Moonshot AI's Kimi K2, narrowing the gap between open models and leading proprietary systems on reasoning-heavy tasks.[3][4] The work also drew attention for its emphasis on the reinforcement-learning infrastructure and stabilization techniques (IcePop, C3PO++, and ASystem) needed to apply large-scale RL to models of this size, contributions that the team published in detail rather than keeping proprietary.[1]

## References

1. inclusionAI / Ling Team. "Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model." arXiv:2510.18855, October 21, 2025. https://arxiv.org/abs/2510.18855
2. inclusionAI. "Ring-1T" model card. Hugging Face. https://huggingface.co/inclusionAI/Ring-1T
3. inclusionAI / AI Wiki. "InclusionAI." https://aiwiki.ai/wiki/inclusionai
4. Interconnects. "Inside a Chinese frontier lab: interview on Ant Group's open model ambitions." https://www.interconnects.ai/p/inside-a-chinese-frontier-lab-inclusion
5. Ant Ling. "Ring-mini-2.0: Small Model, Great Intelligence." Medium. https://ant-ling.medium.com/ring-mini-2-0-small-model-great-intelligence-38040fdf5dff
6. Ant Ling. "Deep Insight, Efficient Inference: Introducing the Trillion-Parameter Ling-1T Model." Medium. https://ant-ling.medium.com/deep-insight-efficient-inference-introducing-the-trillion-parameter-ling-1t-model-77d6170e5e8e
7. Codersera. "Ring-2.6-1T: Ant Group's Open Trillion-Parameter Reasoning Model." 2026. https://codersera.com/blog/ring-2-6-1t-ant-group-trillion-parameter-reasoning-model-2026/
8. SiliconFlow. "Ring-1T Now on SiliconFlow: The World's First Open-Source Trillion-Parameter Thinking Model." https://www.siliconflow.com/blog/ring-1t-now-on-siliconflow-the-world-s-first-open-source-trillion-parameter-thinking-model