Model profile
Ling 2.6 Flash
InclusionAIdeveloper
#232 / 267overall rank
4eval lineages
Evidence summary
Ling 2.6 Flash has an estimated overall rank of #232; its 90% source-sensitivity interval is #102–#262. Its behavior-only rank is #236; company governance moves the combined estimate to #232. Published evidence spans 4 evals and 5 of 7 behavior components. Its strongest relative result is SABER (scenario_c_safety_rate, #4 of 13); its weakest is AA-Omniscience (hallucination_rate, #303 of 311).
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
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 |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #303 / 311 | 0.958 | ↓ lower | Source ↗official | |
| SABERoverall_safety_rate | #7 / 13 | 24.63 | ↑ higher | Source ↗official | |
| SABERscenario_a_safety_rate | #10 / 13 | 25.79 | ↑ higher | Source ↗official | |
| SABERscenario_b_safety_rate | #8 / 13 | 30.66 | ↑ higher | Source ↗official | |
| SABERscenario_c_safety_rate | #4 / 13 | 18.68 | ↑ higher | Source ↗official | |
| SM-Benchadversarial | #49 / 73 | 79.51 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #62 / 73 | 73.21 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #56 / 73 | 85.86 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #55 / 73 | 56.46 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #66 / 73 | 26.23 | ↑ higher | Source ↗official | |
| TACbase_welfare_rate | #59 / 68 | 19.23 | ↑ higher | Source ↗self run |