Model profile
Internlm Chat 7B
Evidence summary
Internlm Chat 7B has an estimated overall rank of #148; its 90% source-sensitivity interval is #39–#215. Its behavior-only rank is #147; company governance moves the combined estimate to #148. Published evidence spans 5 evals and 4 of 7 behavior components. Its strongest relative result is FLAMES (legality, #1 of 13); its weakest is SALAD-Bench (mcq_representation_toxicity, #30 of 33).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗internlm/internlm-chat-7b
- 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 |
|---|---|---|---|---|---|
| Fake Alignment (FINE)multiple_choice_safe_decision_rate | #6 / 14 | 57.33 | ↑ higher | Source ↗official | |
| Fake Alignment (FINE)open_ended_safe_response_rate | #11 / 14 | 92 | ↑ higher | Source ↗official | |
| FLAMESdata_protection | #2 / 13 | 61.84 | ↑ higher | Source ↗official | |
| FLAMESfairness | #2 / 13 | 44.58 | ↑ higher | Source ↗official | |
| FLAMESlegality | #1 / 13 | 76.09 | ↑ higher | Source ↗official | |
| FLAMESmorality | #3 / 13 | 51.24 | ↑ higher | Source ↗official | |
| FLAMESsafety | #5 / 13 | 35.9 | ↑ higher | Source ↗official | |
| SafetyBenchEM | #6 / 21 | 75.4 | ↑ higher | Source ↗official | |
| SafetyBenchIA | #8 / 21 | 79.5 | ↑ higher | Source ↗official | |
| SafetyBenchMH | #6 / 21 | 84.3 | ↑ higher | Source ↗official | |
| SafetyBenchOFF | #12 / 21 | 67.2 | ↑ higher | Source ↗official | |
| SafetyBenchPH | #7 / 21 | 74.15 | ↑ higher | Source ↗official | |
| SafetyBenchPP | #7 / 21 | 78.7 | ↑ higher | Source ↗official | |
| SafetyBenchUB | #8 / 21 | 64.75 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_human_autonomy_integrity | #11 / 33 | 21.12 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_information_safety_harms | #16 / 33 | 16.61 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_malicious_use | #12 / 33 | 22.51 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_misinformation_harms | #11 / 33 | 19.9 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_representation_toxicity | #9 / 33 | 23.71 | ↑ higher | Source ↗official | |
| SALAD-Benchattack_enhanced_socioeconomic_harms | #11 / 33 | 22.08 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_human_autonomy_integrity | #10 / 33 | 96.85 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_information_safety_harms | #15 / 33 | 95.13 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_malicious_use | #12 / 33 | 96.28 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_misinformation_harms | #5 / 33 | 97.05 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_representation_toxicity | #7 / 33 | 94.37 | ↑ higher | Source ↗official | |
| SALAD-Benchbase_socioeconomic_harms | #15 / 33 | 90.95 | ↑ 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 | #30 / 33 | 0.0641 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_misinformation_harms | #30 / 33 | 0 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_representation_toxicity | #30 / 33 | 0.1042 | ↑ higher | Source ↗official | |
| SALAD-Benchmcq_socioeconomic_harms | #30 / 33 | 0 | ↑ higher | Source ↗official | |
| SuperCLUE Safetyinstruction_attack | #20 / 31 | 58.62 | ↑ higher | Source ↗official | |
| SuperCLUE Safetyresponsible_ai | #28 / 31 | 45.45 | ↑ higher | Source ↗official | |
| SuperCLUE Safetytraditional_safety | #28 / 31 | 65.96 | ↑ higher | Source ↗official |
