Ring-1T: benchmark results
InclusionAI's open 1T-parameter Ring 1T reasoning MoE (October 2025). Provider: InclusionAI. Released 2025-07-01. Access: Open.
Aggregate Rating 1647 ± 19, rank #319 of 1656 rated models, from 126 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AGI-Eval Community - General Reasoning | 97.49 | Accuracy (%) | 95 |
| AA AIME 2025 | 89.33 | Accuracy (%) | 88.6 |
| ConStory-Bench | 0.54 | CED errors per 10K words (lower is better) | 81.2 |
| OpenCompass Knowledge - Science (CompassBench 2601) | 94.8 | Score (%) | 80 |
| UGI - Natural Intelligence | 33.69 | NatInt Score | 78.8 |
| OpenCompass Math - College (CompassBench 2601) | 74.8 | Score (%) | 76 |
| AA Omniscience - Software Engineering (SWE) - Julia | 20 | Accuracy (%) | 75.4 |
| AGI-Eval Community - Learning (English) | 93.24 | Accuracy (%) | 75.4 |
| Kagi LLM Benchmark | 66.4 | Accuracy (%) | 74.6 |
| OpenCompass Language - Dialogue (CompassBench 2601) | 98 | Score (%) | 74 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 24 | Accuracy (%) | 72.5 |
| AA LiveCodeBench | 64.34 | Pass@1 (%) | 71.1 |
Interactive version: theaggregate.ai/model?slug=ring-1t · How It Works · Data refreshed daily, snapshot 2026-10-20.