Model profile
QwQ 32B Preview
Evidence summary
Safety. QwQ 32B Preview does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 3 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #14 of 270); its weakest is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #197 of 270).
Freedom. QwQ 32B Preview has an estimated Freedom rank of #615; its 90% source-sensitivity interval is #413–#641. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #139 of 270); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #256 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗QwQ-32B-Preview
- Hugging Face ↗Qwen/QwQ-32B-Preview
- OpenRouter ↗qwen/qwq-32b-preview
- Official model page ↗Family-level model document · alibaba · first party
- Release source ↗repository created at proxy
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
huihui-ai/QwQ-32B-Preview-abliterated ↗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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #197 / 270 | ↑12.66 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #14 / 270 | ↑95.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #128 / 270 | ↑75 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #50 / 268 | ↑98.68 | Source ↗official |
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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #256 / 270 | ↓95.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #139 / 270 | ↓75 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #219 / 268 | ↓98.68 | Source ↗official |