Model profile
Qwen1.5 1.8B Chat
Alibabadeveloper
2024-02-04release date
#264 / 267overall rank
4eval lineages
Evidence summary
Qwen1.5 1.8B Chat has an estimated overall rank of #264; its 90% source-sensitivity interval is #229–#266. Its behavior-only rank is #261; company governance moves the combined estimate to #264. Published evidence spans 4 evals and 5 of 7 behavior components. Its strongest relative result is Open LLM Safety Index (jailbreakbench_safety_rate, #10 of 21); its weakest is CRiskEval (malicious_coordination, #17 of 17).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗Qwen/Qwen1.5-1.8B-Chat
- 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 |
|---|---|---|---|---|---|
| CRiskEvaldeception_willingness | #17 / 17 | 40.43 | ↓ lower | Source ↗official | |
| CRiskEvaldesire_for_resource | #17 / 17 | 54.51 | ↓ lower | Source ↗official | |
| CRiskEvalharmful_goal | #17 / 17 | 59.98 | ↓ lower | Source ↗official | |
| CRiskEvalimprovement_intent | #13 / 17 | 52.36 | ↓ lower | Source ↗official | |
| CRiskEvalmalicious_coordination | #17 / 17 | 43.82 | ↓ lower | Source ↗official | |
| CRiskEvalself_preservation | #14 / 17 | 41.59 | ↓ lower | Source ↗official | |
| CRiskEvalsituational_awareness | #17 / 17 | 70.93 | ↓ lower | Source ↗official | |
| Open LLM Safety Indexjailbreakbench_safety_rate | #10 / 21 | 0.4 | ↑ higher | Source ↗official | |
| Open LLM Safety Indexstrongreject_safety_rate | #11 / 21 | 0.2667 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_human_autonomy_integrity | #29 / 33 | 6.03 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_information_safety_harms | #20 / 33 | 7.82 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_malicious_use | #28 / 33 | 4.98 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_misinformation_harms | #26 / 33 | 6.74 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_representation_toxicity | #21 / 33 | 8.18 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_socioeconomic_harms | #27 / 33 | 7.36 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_human_autonomy_integrity | #29 / 33 | 68.32 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_information_safety_harms | #30 / 33 | 70.21 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_malicious_use | #30 / 33 | 56.36 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_misinformation_harms | #30 / 33 | 73.46 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_representation_toxicity | #30 / 33 | 64.05 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_socioeconomic_harms | #30 / 33 | 74.03 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_human_autonomy_integrity | #30 / 33 | 0 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_information_safety_harms | #30 / 33 | 0 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_malicious_use | #31 / 33 | 0 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_misinformation_harms | #30 / 33 | 0 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_representation_toxicity | #31 / 33 | 0 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_socioeconomic_harms | #30 / 33 | 0 | ↑ higher | Source ↗official | |
| SORRY-Benchavg | #47 / 51 | 0.74 | ↓ lower | Source ↗official |