Inkling Small — benchmark results
Provider: Thinking Machines. Released 2026-07-30. Access: Open.
Unified ELO 1782 ± 15, rank #182 of 1839 rated models, from 64 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI CorpFin v2 | 69.62 | Accuracy (%) | 96.9 |
| ProphetArena | 0.96 | 1 - Brier Score | 95.2 |
| SEAL - AudioMultiChallenge - Text Output | 54.87 | Score | 94.1 |
| AA GPQA Diamond | 89.49 | Accuracy (%) | 91.7 |
| AA Omniscience - Software Engineering (SWE) - Rust | 76 | Accuracy (%) | 90.8 |
| Vals AI TaxEval v2 | 75.51 | Accuracy (%) | 90.3 |
| AA Humanity's Last Exam | 31.6 | Accuracy (%) | 89.7 |
| Epoch AI - Scicode | 48.73 | Score | 89.5 |
| Artificial Analysis Intelligence Index | 40.17 | Intelligence Index | 89.4 |
| AA CritPt | 8.29 | Accuracy (%) | 88.1 |
| Vals AI SWE-bench Verified | 82.2 | Resolved (%) | 86.8 |
| BenchLM | 65.4 | Overall Score | 85.3 |
Interactive version: theaggregate.ai/model?slug=inkling-small · How It Works · Data refreshed daily, snapshot 2026-08-05.