Model profile
Qwen2.5 Coder 3B Instruct
2024-11-06release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is Open LLM Safety Index (jailbreakbench_safety_rate, #10 of 21); its weakest is Open LLM Safety Index (strongreject_safety_rate, #12 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-Coder-3B-Instruct
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
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 |
|---|---|---|---|---|---|
| Open LLM Safety Indexjailbreakbench_safety_rate | #10 / 21 | 0.4 | ↑ higher | Source ↗official | |
| Open LLM Safety Indexstrongreject_safety_rate | #12 / 21 | 0.2 | ↑ higher | Source ↗official |