Model profile
openchatdeveloper
2023-07-30release date
Not rankedSafety rank
Not rankedFreedom rank
Evidence summary
Safety. Openchat 13B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 3 of 7 components. Its strongest relative result is SafetyBench (UB, #11 of 21); its weakest is SafetyBench (PH, #17 of 21).
Freedom. Openchat 13B does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|
| SafetyBenchEM | #16 / 21 | ↑56.6 | Source ↗official | |
| SafetyBenchIA | #17 / 21 | ↑66.6 | Source ↗official | |
| SafetyBenchMH | #16 / 21 | ↑73.1 | Source ↗official | |
| SafetyBenchOFF | #16 / 21 | ↑52.6 | Source ↗official | |
| SafetyBenchPH | #17 / 21 | ↑59.9 | Source ↗official | |
| SafetyBenchPP | #14 / 21 | ↑71.1 | Source ↗official | |
| SafetyBenchUB | #11 / 21 | ↑62.6 | Source ↗official |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.