Model profile
Inkling
Thinking Machines Labdeveloper
2026-07-14release date
#34 / 267overall rank
7eval lineages
1discovery sources
Evidence summary
Inkling has an estimated overall rank of #34; its 90% source-sensitivity interval is #8–#162. Its behavior-only rank is #29; company governance moves the combined estimate to #34. Published evidence spans 7 evals and 6 of 7 behavior components. Its strongest relative result is SM-Bench (ambiguous_interpretation, #2 of 73); its weakest is SM-Bench (eq_boundaries, #68 of 73).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗inkling
- Hugging Face ↗thinkingmachines/Inkling
- OpenRouter ↗thinkingmachines/inkling
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
- thinkingmachines.ai ↗
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 | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #77 / 311 | 0.6311 | ↓ lower | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #36 / 260 | 39.02 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #66 / 260 | 91.33 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #24 / 260 | 97.78 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #80 / 258 | 98 | ↑ higher | Source ↗official | |
| Inkling-Small model card — FORTRESSbenign_answer_rate | #4 / 10 | 95.9 | ↑ higher | Source ↗official | |
| Inkling-Small model card — FORTRESSharmful_refusal_rate | #4 / 10 | 78 | ↑ higher | Source ↗official | |
| Inkling-Small model card — StrongREJECTsafety_rate | #6 / 10 | 98.6 | ↑ higher | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #25 / 31 | 8.933 | ↓ lower | Source ↗self run | |
| SM-Benchadversarial | #33 / 73 | 82.44 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #2 / 73 | 96.73 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #59 / 73 | 83.25 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #68 / 73 | 48.03 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #36 / 73 | 72.68 | ↑ higher | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #19 / 102 | 6.97 | ↑ higher | Source ↗official | |
| SpeciEvalland_animal_4ns | #7 / 102 | 3.92 | ↓ lower | Source ↗official | |
| SpeciEvalsea_animal_4ns | #6 / 102 | 4.23 | ↓ lower | Source ↗official | |
| SpeciEvalspeciesism | #12 / 102 | 1.48 | ↓ lower | Source ↗official | |
| TACbase_welfare_rate | #39 / 68 | 25.64 | ↑ higher | Source ↗self run |