Ling 3.1 Flash 1019: benchmark results
InclusionAI's Ling-3.1-flash-1019, a released hybrid-linear mixture-of-experts model with publisher-nominal 560B total and 25B active parameters and a 1M-token context window. The 1019 post-training revision and the base checkpoint remain distinct identities. Provider: InclusionAI. Released 2026-10-27. Access: Open.
Aggregate Rating 1796 ± 22, rank #97 of 10916 rated models, from 73 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AutomationBench-AA - HR - Raw Objective Completion | 80.2 | Raw Objective Completion (%) | 98 |
| AutomationBench-AA - Finance - Raw Objective Completion | 92.18 | Raw Objective Completion (%) | 96.8 |
| AutomationBench-AA - Sales - Raw Objective Completion | 88.56 | Raw Objective Completion (%) | 96.4 |
| AutomationBench-AA | 67.55 | Guardrail-Adjusted Objective Completion (%) | 95.1 |
| AutomationBench-AA - Support - Raw Objective Completion | 91.5 | Raw Objective Completion (%) | 95.1 |
| AA GDPval | 1652.94 | ELO | 93.2 |
| AA CritPt | 26 | Accuracy (%) | 92.8 |
| AA Long Context Reasoning | 82.33 | Accuracy (%) | 92.3 |
| AA-Briefcase - XLSX - Rubric Pass Rate | 56.14 | Rubric Pass Rate (%) | 92.1 |
| AA-Briefcase - Analytical Quality Elo | 1794.74 | Elo | 91.3 |
| AA Humanity's Last Exam | 43.47 | Accuracy (%) | 91 |
| AutomationBench-AA - Strict | 35.16 | Strict Task Success (%) | 90.7 |
Interactive version: theaggregate.ai/model?slug=ling-3-1-flash-1019 · How It Works · Data refreshed daily, snapshot 2026-11-08.