Model profile
Ling 2.6 Flash
Evidence summary
Safety. Ling 2.6 Flash has an estimated Safety rank of #299; its 90% source-sensitivity interval is #141–#340. Its behavior-only rank is #304; company governance moves the combined estimate to #299. Published Safety evidence spans 4 eval lineages and 5 of 7 components. Its strongest relative result is SABER (scenario_c_safety_rate, #4 of 13); its weakest is AA-Omniscience (hallucination_rate, #353 of 358).
Freedom. Ling 2.6 Flash has an estimated Freedom rank of #609; its 90% source-sensitivity interval is #380–#661. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is SM-Bench (adversarial, #25 of 92); its weakest is SM-Bench (overfit, #85 of 92).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗ling-2-6-flash
- OpenRouter ↗inclusionai/ling-2.6-flash
- Official model page ↗Family-level model document · inclusion ai · first party
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 | #353 / 358 | ↓0.9672 | Source ↗official | |
| SABERoverall_safety_rate | #7 / 13 | ↑24.63 | Source ↗official | |
| SABERscenario_a_safety_rate | #10 / 13 | ↑25.79 | Source ↗official | |
| SABERscenario_b_safety_rate | #8 / 13 | ↑30.66 | Source ↗official | |
| SABERscenario_c_safety_rate | #4 / 13 | ↑18.68 | Source ↗official | |
| SM-Benchadversarial | #64 / 92 | ↑79.51 | Source ↗official | |
| SM-Benchambiguous_interpretation | #81 / 92 | ↑73.21 | Source ↗official | |
| SM-Benchanti_hallucination | #74 / 92 | ↑85.86 | Source ↗official | |
| SM-Bencheq_boundaries | #73 / 92 | ↑56.46 | Source ↗official | |
| SM-Benchoverfit | #85 / 92 | ↑26.23 | Source ↗official | |
| TACbase_welfare_rate | #77 / 92 | ↑19.23 | Source ↗self run |
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.