Model profile
Qwen 14B Chat
Alibabadeveloper
2023-09-25release date
#112 / 267overall rank
8eval lineages
Evidence summary
Qwen 14B Chat has an estimated overall rank of #112; its 90% source-sensitivity interval is #42–#186. Its behavior-only rank is #102; company governance moves the combined estimate to #112. Published evidence spans 8 evals and 4 of 7 behavior components. Its strongest relative result is CMoralEval (familial_morality, #2 of 26); its weakest is FLAMES (fairness, #11 of 13).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗qwen/qwen-14b-chat
- Official model page ↗Family-level model document · alibaba · first party
- 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 |
|---|---|---|---|---|---|
| CMoralEvalfamilial_morality | #2 / 26 | 0.59 | ↑ higher | Source ↗official | |
| CMoralEvalinternet_ethics | #2 / 26 | 0.55 | ↑ higher | Source ↗official | |
| CMoralEvalpersonal_morality | #2 / 26 | 0.54 | ↑ higher | Source ↗official | |
| CMoralEvalprofessional_ethics | #2 / 26 | 0.57 | ↑ higher | Source ↗official | |
| CMoralEvalsocial_morality | #2 / 26 | 0.56 | ↑ higher | Source ↗official | |
| Fake Alignment (FINE)multiple_choice_safe_decision_rate | #3 / 14 | 69.33 | ↑ higher | Source ↗official | |
| Fake Alignment (FINE)open_ended_safe_response_rate | #3 / 14 | 98.67 | ↑ higher | Source ↗official | |
| FLAMESdata_protection | #3 / 13 | 55.26 | ↑ higher | Source ↗official | |
| FLAMESfairness | #11 / 13 | 30.92 | ↑ higher | Source ↗official | |
| FLAMESlegality | #9 / 13 | 32.61 | ↑ higher | Source ↗official | |
| FLAMESmorality | #1 / 13 | 54.23 | ↑ higher | Source ↗official | |
| FLAMESsafety | #4 / 13 | 36.83 | ↑ higher | Source ↗official | |
| HarmBenchdr | #10 / 28 | 16.5 | ↓ lower | Source ↗official | |
| S-Evalbase_en_overall | #6 / 22 | 73.5 | ↑ higher | Source ↗official | |
| SafeDialBenchaggression | #7 / 18 | 7.15 | ↑ higher | Source ↗official | |
| SafeDialBenchethics | #2 / 18 | 7.68 | ↑ higher | Source ↗official | |
| SafeDialBenchfairness | #11 / 18 | 7.27 | ↑ higher | Source ↗official | |
| SafeDialBenchlegality | #4 / 18 | 7.987 | ↑ higher | Source ↗official | |
| SafeDialBenchmorality | #2 / 18 | 7.437 | ↑ higher | Source ↗official | |
| SafeDialBenchprivacy | #3 / 18 | 7.69 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_human_autonomy_integrity | #22 / 33 | 9.91 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_information_safety_harms | #24 / 33 | 6.51 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_malicious_use | #18 / 33 | 10.44 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_misinformation_harms | #23 / 33 | 8.39 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_representation_toxicity | #22 / 33 | 7.44 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_socioeconomic_harms | #24 / 33 | 7.79 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_human_autonomy_integrity | #8 / 33 | 97.32 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_information_safety_harms | #12 / 33 | 96.34 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_malicious_use | #8 / 33 | 97.33 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_misinformation_harms | #13 / 33 | 95.42 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_representation_toxicity | #13 / 33 | 92.21 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_socioeconomic_harms | #9 / 33 | 93.07 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_human_autonomy_integrity | #7 / 33 | 61.94 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_information_safety_harms | #7 / 33 | 51.11 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_malicious_use | #8 / 33 | 54.74 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_misinformation_harms | #7 / 33 | 55 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_representation_toxicity | #8 / 33 | 55.42 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_socioeconomic_harms | #6 / 33 | 55.56 | ↑ higher | Source ↗official | |
| SuperCLUE Safetyinstruction_attack | #9 / 31 | 68.97 | ↑ higher | Source ↗official | |
| SuperCLUE Safetyresponsible_ai | #13 / 31 | 61.82 | ↑ higher | Source ↗official | |
| SuperCLUE Safetytraditional_safety | #21 / 31 | 72.34 | ↑ higher | Source ↗official |