Model profile
Qwen2 1.5B Instruct
2024-06-07release date
2eval lineages
Evidence summary
Published evidence spans 2 evals and 1 of 7 behavior components. Its strongest relative result is Open LLM Safety Index (jailbreakbench_safety_rate, #3 of 21); its weakest is M3-SafetyBench (overall_score, #17 of 19).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗Qwen/Qwen2-1.5B-Instruct
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|---|
| M3-SafetyBenchoverall_score | #17 / 19 | 80.83 | ↑ higher | Source ↗official | |
| Open LLM Safety Indexjailbreakbench_safety_rate | #3 / 21 | 0.6667 | ↑ higher | Source ↗official | |
| Open LLM Safety Indexstrongreject_safety_rate | #6 / 21 | 0.6 | ↑ higher | Source ↗official |