Model profile
Internlm Chat 7B V1.1
2023-07-06release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 3 of 7 behavior components. Its strongest relative result is SafetyBench (EM, #2 of 21); its weakest is SafetyBench (OFF, #11 of 21).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Official model page ↗Family-level model document · internlm · 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 |
|---|---|---|---|---|---|
| SafetyBenchEM | #2 / 21 | 78.8 | ↑ higher | Source ↗official | |
| SafetyBenchIA | #4 / 21 | 82.65 | ↑ higher | Source ↗official | |
| SafetyBenchMH | #4 / 21 | 85.5 | ↑ higher | Source ↗official | |
| SafetyBenchOFF | #11 / 21 | 67.35 | ↑ higher | Source ↗official | |
| SafetyBenchPH | #4 / 21 | 76.65 | ↑ higher | Source ↗official | |
| SafetyBenchPP | #5 / 21 | 80.7 | ↑ higher | Source ↗official | |
| SafetyBenchUB | #5 / 21 | 66.3 | ↑ higher | Source ↗official |