Model profile
Ling 3.0 Flash VL
Evidence summary
Safety. Ling 3.0 Flash VL 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 AA-Omniscience (hallucination_rate, #13 of 358); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #263 of 270).
Freedom. Ling 3.0 Flash VL has an estimated Freedom rank of #364; its 90% source-sensitivity interval is #220–#471. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #7 of 270); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #217 of 270).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗ling-3-0-flash-vl
- Hugging Face ↗inclusionAI/Ling-3.0-flash-VL
- 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 |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #13 / 358 | ↓0.2205 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #241 / 270 | ↑9.56 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #263 / 270 | ↑47.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #50 / 270 | ↑94.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #102 / 268 | ↑97.27 | 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 | #7 / 270 | ↓47.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #217 / 270 | ↓94.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #161 / 268 | ↓97.27 | Source ↗official |