Model profile
Qwen2.5 7B Instruct 1M
Evidence summary
Safety. Qwen2.5 7B Instruct 1M 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 (cbrn_attack_non_success_rate, #141 of 270); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #203 of 270).
Freedom. Qwen2.5 7B Instruct 1M has an estimated Freedom rank of #174; its 90% source-sensitivity interval is #61–#589. 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, #66 of 270); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #126 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Official model page ↗Family-level model document · alibaba · first party
- 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 | #180 / 270 | ↑13.18 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #141 / 270 | ↑87 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #203 / 270 | ↑52.22 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #191 / 268 | ↑94.18 | 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 | #126 / 270 | ↓87 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #66 / 270 | ↓52.22 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #78 / 268 | ↓94.18 | Source ↗official |