Model profile
Apertus 70B Instruct
Evidence summary
Safety. Apertus 70B Instruct does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 4 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #28 of 246); its weakest is AA-Omniscience (hallucination_rate, #198 of 345).
Freedom. Apertus 70B Instruct has an estimated Freedom rank of #498; its 90% source-sensitivity interval is #213–#595. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #129 of 248); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #217 of 246).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗apertus-70b-instruct
- Release source ↗curated outward evidence
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 |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #198 / 345 | ↓0.8282 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #103 / 248 | ↑18.09 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #67 / 248 | ↑90.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #117 / 248 | ↑73.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #28 / 246 | ↑99.36 | 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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #178 / 248 | ↓90.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #129 / 248 | ↓73.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #217 / 246 | ↓99.36 | Source ↗official |