Model profile
InternLM3 8B Instruct
Evidence summary
Safety. InternLM3 8B Instruct does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 1 of 7 components. Its strongest relative result is FinEval 6.0 Safety Awareness (safety_awareness_score, #7 of 8); its weakest is FinEval 6.0 Safety Awareness (safety_awareness_score, #7 of 8).
Freedom. InternLM3 8B Instruct has an estimated Freedom rank of #74; its 90% source-sensitivity interval is #9–#440. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is UGI Leaderboard — base-model willingness (willingness_direct_score, #4 of 156); its weakest is UGI Leaderboard — base-model willingness (willingness_adherence_score, #25 of 156).
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 ↗repository created at proxy
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| FinEval 6.0 Safety Awarenesssafety_awareness_score | #7 / 8 | ↑73.52 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| UGI Leaderboard — base-model willingnesswillingness_adherence_score | #25 / 156 | ↑6 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_direct_score | #4 / 156 | ↑6 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.