New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Ring-1T
About Ring-1T
Ring-1T is an AI model developed by Ant Group, in the language category, released in 2025, made available as an open-weights model with 1000B params.
On this page you'll find Ring-1T's full specifications, including 25 benchmark results. Review provider pricing and benchmark scores below, or compare Ring-1T head-to-head with other language models.
Links
Run Ring-1T locally — what it takes
Ring-1T (1,000B) is too large to run on a single consumer or Apple machine. At Q4 its weights alone are about 560 GB — it needs a multi-GPU / datacenter setup:
- ≈ 3× AMD Instinct MI325X
- ≈ 4× NVIDIA B200
Lower quantization (Q3/Q2) or CPU + system-RAM offload (e.g. ktransformers) reduces the requirement at the cost of speed.
Software support
✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.
Community
No reports yet. Own this model on some hardware? Be the first to confirm it runs.
No comments yet. Start the discussion.
Ring-1T benchmark scores▶
| Benchmark | Category | Score | Variant |
|---|---|---|---|
| Codeforces Elo | code | 2,088 | thinking-rating |
| LiveCodeBench v6 | code | 78.3% | thinking-avg@4 |
| Aider Benchmark | coding | 78.57 | thinking |
| ArenaHard v2 | general | 81.59 | thinking-win-rate |
| C-Eval | general | 91.53% | thinking |
| IFEval | general | 85.21% | thinking |
| MMLU-Pro | general | 80.54% | thinking |
| MultiChallenge | general | 50.92% | thinking |
| AGIEval | knowledge | 88.13 | thinking |
| CMMLU | knowledge | 89.14 | thinking |
| TriviaQA | knowledge | 78.59 | thinking |
| AIME 2025 | math | 93.4% | thinking-avg@64 |
| CNMO 2024 | math | 88.54% | thinking |
| HMMT February 2025 | math | 86.72% | thinking-avg@16 |
| Omni-MATH | math | 82.63 | thinking |
| UGMathBench | math | 76.47 | thinking |
| ARC-AGI-1 | reasoning | 55.94 | thinking |
| BBEH | reasoning | 59.63 | thinking |
| FinanceReasoning | reasoning | 87.42 | thinking |
| GPQA Diamond | reasoning | 78.63% | thinking |
| Humanity's Last Exam | reasoning | 16.03% | thinking |
| ZebraLogic | reasoning | 95.15% | thinking |
| HealthBench | safety | 57.93% | thinking |
| PhyBench | science | 42.65 | thinking |
| BFCL v3 | tool-use | 68.82% | thinking |
More models like Ring-1T
Frequently asked questions
What is Ring-1T? ▶
Ring-1T is an AI model developed by Ant Group, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.
Who created Ring-1T? ▶
Ring-1T was developed by Ant Group and released in 2025.
Is Ring-1T open source or proprietary? ▶
Ring-1T ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.
How much does Ring-1T cost? ▶
Pricing for Ring-1T depends on the provider. See the providers table on this page for the latest API rates.
How does Ring-1T perform on benchmarks? ▶
Ring-1T is benchmarked across 25 evaluations on GenAIList, including Codeforces Elo (2,088). See the full benchmark table below and compare it with other models.
Know a great video about Ring-1T?
Add YouTube Video
Add Tweet/Discussion
Report an Issue
Help us maintain accurate information in our database.
Suggest an Edit
Tell us what needs to be changed or corrected for