Inkling Small (xHigh): benchmark results
Provider: Thinking Machines. Released 2026-07-30. Access: Open.
Aggregate Rating 1654 ± 33, rank #532 of 2245 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Epoch AI - GPQA Diamond | 88.51 | Accuracy (%) | 79.1 |
| SecureBio BioTIER Permit | 99.8 | Benign prompts answered (%) | 78.9 |
| OTIS Mock AIME 2024-25 | 90 | Accuracy (%) | 72.5 |
| SecureBio HPCT | 54.91 | Accuracy (%) | 63.4 |
| ARC-AGI-1 | 84 | Accuracy (%) | 58.1 |
| ARC-AGI-2 | 40.14 | Accuracy (%) | 56.5 |
| FrontierMath - Tiers 1-3 (v2) | 46.32 | Accuracy (%, 285 private v2 problems) | 56.1 |
| SecureBio ABLE Full | 57.5 | Accuracy (%) | 52.6 |
| SecureBio ABLE Tasks With Baselines Only | 34.49 | Accuracy (%) | 52.6 |
| FrontierMath - Tier 4 (v2) | 17.07 | Accuracy (%, 41 private v2 problems) | 28.4 |
| SecureBio BioTIER Refuse | 24.9 | Hazardous prompts refused (%) | 27.6 |
| SecureBio VCT v2 | 34.46 | Accuracy (%) | 15.4 |
Interactive version: theaggregate.ai/model?slug=inkling-small-xhigh · How It Works · Data refreshed daily, snapshot 2026-11-16.