Model profile
Qwen2-VL 72B Instruct
Evidence summary
Safety. Qwen2-VL 72B Instruct does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 3 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #95 of 270); its weakest is SafeArena (normalized_safety_score, #5 of 5).
Freedom. Qwen2-VL 72B Instruct has an estimated Freedom rank of #358; its 90% source-sensitivity interval is #193–#586. 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, #92 of 272); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #176 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗Qwen/Qwen2-VL-72B-Instruct
- 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 | #160 / 272 | ↑14.73 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #167 / 272 | ↑84.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #179 / 272 | ↑58.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #95 / 270 | ↑97.59 | Source ↗official | |
| SafeArenanormalized_safety_score | #5 / 5 | ↑21.5 | 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 | #103 / 272 | ↓84.67 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #92 / 272 | ↓58.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #176 / 270 | ↓97.59 | Source ↗official |