Ring-1T ↗
- source model id
- inclusionAI/Ring-1T
- hosting
- siliconflow-hosted
- platforms
- SiliconFlow
- architecture
- input_modalities
- text
- output_modalities
- text
- capabilities
- structuredOutputs
- toolCalling
Ring-1T is an open-source, trillion-parameter thinking model released by the Bailing team. Built upon the Ling 2.0 architecture and the Ling-1T-base foundation model, it features 1 trillion total par…
siliconFlow/inclusionAI/Ring-1T
Ring-1T is an open-source, trillion-parameter thinking model released by the Bailing team. Built upon the Ling 2.0 architecture and the Ling-1T-base foundation model, it features 1 trillion total parameters with 50 billion activated parameters and supports a context window of up to 131K tokens. The model's deep reasoning and natural language inference capabilities have been significantly enhanced through large-scale verifiable reward reinforcement learning (RLVR), combined with the self-developed icepop reinforcement learning stabilization method and the efficient ASystem RL framework. Ring-1T achieves leading open-source performance on challenging reasoning benchmarks, including math competitions (e.g., IMO 2025), code generation (e.g., ICPC World Finals 2025), and logical reasoning
1–1 / 1
1–1 / 1
1–6 / 6
Hugging Face · Model reference ↗
1–2 / 2
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.