Model profile
Qwen2.5 3B Instruct
Evidence summary
Safety. Qwen2.5 3B Instruct has an estimated Safety rank of #283; its 90% source-sensitivity interval is #65–#330. Its behavior-only rank is #275; company governance moves the combined estimate to #283. Published Safety evidence spans 3 eval lineages and 3 of 7 components. Its strongest relative result is Open LLM Safety Index (jailbreakbench_safety_rate, #4 of 21); its weakest is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #209 of 248).
Freedom. Qwen2.5 3B Instruct has an estimated Freedom rank of #203; its 90% source-sensitivity interval is #71–#483. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #41 of 248); its weakest is Open LLM Safety Index (jailbreakbench_safety_rate, #16 of 21).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗Qwen/Qwen2.5-3B-Instruct
- 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.
- ArRENCEAI/Qwen2.5-3B-Instruct-OBLITERATED ↗Direct non-quantized finetune documented by Hugging Face metadata
- kikichi/Qwen2.5-3B-Instruct-Uncensored ↗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 | #209 / 248 | ↑10.59 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #140 / 248 | ↑87 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #208 / 248 | ↑41.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #159 / 246 | ↑95.09 | Source ↗official | |
| Open LLM Safety Indexjailbreakbench_safety_rate | #4 / 21 | ↑0.6 | Source ↗official | |
| Open LLM Safety Indexstrongreject_safety_rate | #8 / 21 | ↑0.3333 | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #14 / 46 | ↑0.99 | 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 | #105 / 248 | ↓87 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #41 / 248 | ↓41.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #88 / 246 | ↓95.09 | Source ↗official | |
| Open LLM Safety Indexjailbreakbench_safety_rate | #16 / 21 | ↓0.6 | Source ↗official | |
| Open LLM Safety Indexstrongreject_safety_rate | #12 / 21 | ↓0.3333 | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #24 / 46 | ↓0.99 | Source ↗official |