Model profile
Inkling Small
Thinking Machines Labdeveloper
2026-07-30release date
#28 / 305overall rank
4eval lineages
Evidence summary
Inkling Small has an estimated overall rank of #28; its 90% source-sensitivity interval is #16–#149. Its behavior-only rank is #20; company governance moves the combined estimate to #28. Published evidence spans 4 evals and 5 of 7 behavior components. Its strongest relative result is TAC (base_welfare_rate, #17 of 74); its weakest is Inkling-Small model card — StrongREJECT (safety_rate, #8 of 10).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗inkling-small
- Hugging Face ↗thinkingmachines/Inkling-Small
- OpenRouter ↗thinkingmachines/inkling-small
- Inkling-Small model card ↗Exact model document · Thinking Machines Lab · first party
- Release source ↗curated outward evidence
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #85 / 327 | ↓0.6299 | Source ↗official | |
| Inkling-Small model card — FORTRESSbenign_answer_rate | #3 / 10 | ↑96.9 | Source ↗official | |
| Inkling-Small model card — FORTRESSharmful_refusal_rate | #7 / 10 | ↑71.6 | Source ↗official | |
| Inkling-Small model card — StrongREJECTsafety_rate | #8 / 10 | ↑98.4 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #22 / 31 | ↓8.9 | Source ↗self run | |
| TACbase_welfare_rate | #17 / 74 | ↑35.26 | Source ↗self run |