Model profile
Inkling
Thinking Machines Labdeveloper
2026-07-14release date
#48 / 312overall rank
9eval lineages
1discovery sources
Evidence summary
Inkling has an estimated overall rank of #48; its 90% source-sensitivity interval is #12–#180. Its behavior-only rank is #47; company governance moves the combined estimate to #48. Published evidence spans 9 evals and 6 of 7 behavior components. Its strongest relative result is SM-Bench (ambiguous_interpretation, #2 of 79); its weakest is SM-Bench (eq_boundaries, #74 of 79).
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 | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #102 / 330 | ↓0.6766 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #33 / 241 | ↑39.02 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #58 / 241 | ↑91.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #20 / 241 | ↑97.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #71 / 239 | ↑98 | Source ↗official | |
| Inkling-Small model card — FORTRESSbenign_answer_rate | #4 / 10 | ↑95.9 | Source ↗official | |
| Inkling-Small model card — FORTRESSharmful_refusal_rate | #4 / 10 | ↑78 | Source ↗official | |
| Inkling-Small model card — StrongREJECTsafety_rate | #6 / 10 | ↑98.6 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #27 / 33 | ↓8.933 | Source ↗self run | |
| Opposite-Narrator Sycophancysycophancy_rate_pct | #13 / 24 | ↓3.5 | Source ↗official | |
| Pander Scoreconversational_absolute_pander_score | #13 / 20 | ↓18.37 | Source ↗official | |
| Pander Scoreinstructional_absolute_pander_score | #12 / 20 | ↓45.4 | Source ↗official | |
| SM-Benchadversarial | #35 / 79 | ↑82.44 | Source ↗official | |
| SM-Benchambiguous_interpretation | #2 / 79 | ↑96.73 | Source ↗official | |
| SM-Benchanti_hallucination | #64 / 79 | ↑83.25 | Source ↗official | |
| SM-Bencheq_boundaries | #74 / 79 | ↑48.03 | Source ↗official | |
| SM-Benchoverfit | #40 / 79 | ↑72.68 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #22 / 113 | ↑6.97 | Source ↗official | |
| SpeciEvalland_animal_4ns | #8 / 113 | ↓3.92 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #7 / 113 | ↓4.23 | Source ↗official | |
| SpeciEvalspeciesism | #15 / 113 | ↓1.48 | Source ↗official | |
| TACbase_welfare_rate | #43 / 76 | ↑25.64 | Source ↗self run |