Ling 3.0 Tiny: benchmark results
Provider: InclusionAI. Released 2026-08-06. Access: Open.
Aggregate Rating 1538 ± 26, rank #649 of 1640 rated models, from 81 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA GPQA Diamond | 73.43 | Accuracy (%) | 54 |
| Tau3 Banking | 20.82 | Success Rate (%) | 52.9 |
| AA Long Context Reasoning | 60.33 | Accuracy (%) | 49.4 |
| AA Humanity's Last Exam | 9.31 | Accuracy (%) | 46.5 |
| AA-Omniscience Accuracy | 37.93 | Accuracy (%) | 43.9 |
| AA-Omniscience Index - Software Engineering (SWE) - C | 29.09 | Omniscience Index | 35 |
| MLCR-AA - Accuracy | 26.67 | Accuracy (%) | 34 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 12.22 | Accuracy (%) | 32.8 |
| AA Terminal-Bench 2.1 | 27.72 | Pass@1 (%) | 31.8 |
| AA-Omniscience Index - Software Engineering (SWE) - PHP | 11.76 | Omniscience Index | 31.3 |
| MLCR-AA | 10 | Overall Score (%) | 31.1 |
| AA-Omniscience Index - Humanities & Social Sciences | -6.44 | Omniscience Index | 28.9 |
Interactive version: theaggregate.ai/model?slug=ling-3-0-tiny · How It Works · Data refreshed daily, snapshot 2026-11-07.