Ring-flash-2.0 — benchmark results
InclusionAI's open 100B MoE thinking model (6.1B active), the RL-trained reasoning counterpart of Ling-flash-2.0 (September 2025). Provider: InclusionAI. Released 2025-09-19. Access: Open.
Unified ELO 1533 ± 69, rank #673 of 1776 rated models, from 38 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA AIME 2025 | 83.67 | Accuracy (%) | 80.4 |
| AA LiveCodeBench | 62.75 | Pass@1 (%) | 68.7 |
| CritPt | 0.3 | Accuracy (self-reported) | 65 |
| AA MMLU-Pro | 79.27 | Accuracy (%) | 63.4 |
| AA Humanity's Last Exam | 8.94 | Accuracy (%) | 58.3 |
| SuiChat-CN | 68.7 | Standard F1 (self-reported) | 58.1 |
| AA GPQA Diamond | 72.53 | Accuracy (%) | 56.9 |
| AA CritPt | 0.28 | Accuracy (%) | 54.4 |
| AA Omniscience - Science, Engineering & Mathematics | 26.1 | Accuracy (%) | 50.4 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 18 | Accuracy (%) | 50 |
| AA Omniscience - Software Engineering (SWE) - Julia | 12 | Accuracy (%) | 47.9 |
| AA Omniscience - Software Engineering (SWE) - Swift | 36 | Accuracy (%) | 47.7 |
Interactive version: theaggregate.ai/model?slug=ring-flash-2-0 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.