Model profile
Evidence summary
Safety. Falcon Mamba 7B Instruct 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 Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #165 of 270); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #258 of 268).
Freedom. Falcon Mamba 7B Instruct has an estimated Freedom rank of #67; its 90% source-sensitivity interval is #16–#383. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #11 of 268); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #96 of 270).
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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #165 / 270 | ↑14.47 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #174 / 270 | ↑83.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #219 / 270 | ↑45.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #258 / 268 | ↑71.09 | 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 | #96 / 270 | ↓83.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #51 / 270 | ↓45.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #11 / 268 | ↓71.09 | Source ↗official |