Inkling 2 Small: benchmark results
Provider: Thinking Machines. Released 2026-11-05. Access: API.
Aggregate Rating 1822 ± 20, rank #50 of 1636 rated models, from 89 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA-AnalystAgent - Pass@1 | 71.25 | Pass@1 (%) | 100 |
| AA-AnalystAgent - Pass@K | 86.25 | Pass@K (%) | 100 |
| AA GDP.pdf - Insurance - Criterion Pass Rate | 90.4 | Criterion Pass Rate (%) | 99.2 |
| EnterpriseBench (CoreCraft Agents) | 71.8 | Score (%) | 96.3 |
| AA Long Context Reasoning | 83.33 | Accuracy (%) | 96.2 |
| EnterpriseOps-Gym-AA - Drive | 63.81 | Task Success (%) | 96 |
| AA GDP.pdf - Legal - Criterion Pass Rate | 85.79 | Criterion Pass Rate (%) | 95.1 |
| AA-Briefcase - Presentation Elo | 1564.08 | Elo | 94.8 |
| EnterpriseOps-Gym-AA - Teams | 50 | Task Success (%) | 94 |
| EnterpriseOps-Gym-AA - Hybrid | 43.14 | Task Success (%) | 93 |
| AA Humanity's Last Exam | 44.11 | Accuracy (%) | 92 |
| AA GDP.pdf - STEM/Research - Criterion Pass Rate | 78.45 | Criterion Pass Rate (%) | 91 |
Interactive version: theaggregate.ai/model?slug=inkling-2-small · How It Works · Data refreshed daily, snapshot 2026-11-06.