Model profile
Qwen2 5 7B Instruct Turbo
1eval lineages
Evidence summary
Published evidence spans 1 evals and 3 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #21 of 260); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #198 of 260).
Compare this model
Only models sharing at least one published sub-eval are listed.
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #21 / 260 | 49.35 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #190 / 260 | 84.33 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #198 / 260 | 48.33 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #147 / 258 | 95.64 | ↑ higher | Source ↗official |