Model profile
Aurora Alpha
2026-02-09release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 3 of 7 behavior components. Its strongest relative result is SM-Bench (ambiguous_interpretation, #61 of 73); its weakest is SM-Bench (adversarial, #69 of 73).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗openrouter/aurora-alpha
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 |
|---|---|---|---|---|---|
| SM-Benchadversarial | #69 / 73 | 70.73 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #61 / 73 | 73.51 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #64 / 73 | 79.06 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #66 / 73 | 51.69 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #67 / 73 | 25.68 | ↑ higher | Source ↗official |