Model profile
Komodo 7B Base
Evidence summary
Safety. Komodo 7B Base 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 (bias_attack_non_success_rate, #9 of 270); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #255 of 268).
Freedom. Komodo 7B Base has an estimated Freedom rank of #385; its 90% source-sensitivity interval is #244–#468. 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, #14 of 268); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #258 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 | #9 / 270 | ↑65.63 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #12 / 270 | ↑95.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #148 / 270 | ↑70.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #255 / 268 | ↑76.21 | Source ↗official | |
| IndoBias-Pairs — parity-aware culturally grounded biasparity_score | #18 / 26 | ↑84.78 | 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 | #258 / 270 | ↓95.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #122 / 270 | ↓70.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #14 / 268 | ↓76.21 | Source ↗official |