Model profile
Step 3.7 Flash
Evidence summary
Safety. Step 3.7 Flash has an estimated Safety rank of #221; its 90% source-sensitivity interval is #59–#290. Its behavior-only rank is #224; company governance moves the combined estimate to #221. Published Safety evidence spans 3 eval lineages and 2 of 7 components. Its strongest relative result is SpeciEval (belief_animal_sentience, #1 of 123); its weakest is SpeciEval (sea_animal_4ns, #111 of 123).
Freedom. Step 3.7 Flash has an estimated Freedom rank of #547; its 90% source-sensitivity interval is #370–#613. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SpeechMap model completion (complete_pct, #126 of 181); its weakest is SpeechMap model completion (complete_pct, #126 of 181).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗step-3-7-flash
- Hugging Face ↗stepfun-ai/Step-3.7-Flash
- NVIDIA ↗qc69jvmznzxy/step-3.7-flash
- OpenRouter ↗stepfun/step-3.7-flash
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
- AEON-7/Step-3.7-Flash-AEON-Ultimate-Abliterated-BF16 ↗Direct non-quantized finetune documented by Hugging Face metadata
- ibrahimkettaneh/Step-3.7-Flash-uncensored-abliterated-heretic-BF16 ↗Direct non-quantized finetune documented by Hugging Face metadata
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #210 / 345 | ↓0.8498 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #1 / 123 | ↑7 | Source ↗self run | |
| SpeciEvalland_animal_4ns | #107 / 123 | ↓4.9 | Source ↗self run | |
| SpeciEvalsea_animal_4ns | #111 / 123 | ↓5.125 | Source ↗self run | |
| SpeciEvalspeciesism | #2 / 123 | ↓1.025 | Source ↗self run | |
| TACbase_welfare_rate | #69 / 87 | ↑19.87 | Source ↗self run |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| SpeechMap model completioncomplete_pct | #126 / 181 | ↑45.4 | Source ↗official |