Model profile
Evidence summary
Safety. OpenThaiGPT1.5 72B 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 ThaiSafetyBench (safety_score, #5 of 18); its weakest is ThaiSafetyBench (safety_score, #5 of 18).
Freedom. OpenThaiGPT1.5 72B Instruct has an estimated Freedom rank of #462; its 90% source-sensitivity interval is #264–#593. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is ThaiSafetyBench (safety_score, #14 of 18); its weakest is ThaiSafetyBench (safety_score, #14 of 18).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- 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 |
|---|---|---|---|---|
| ThaiSafetyBenchsafety_score | #5 / 18 | ↑87.66 | 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 |
|---|---|---|---|---|
| ThaiSafetyBenchsafety_score | #14 / 18 | ↓87.66 | Source ↗official |