Model profile
Longcat 2.0
Evidence summary
Safety. Longcat 2.0 has an estimated Safety rank of #137; its 90% source-sensitivity interval is #86–#244. Its behavior-only rank is #138; company governance moves the combined estimate to #137. Published Safety evidence spans 3 eval lineages and 5 of 7 components. Its strongest relative result is SM-Bench (eq_boundaries, #16 of 84); its weakest is SM-Bench (anti_hallucination, #78 of 84).
Freedom. Longcat 2.0 has an estimated Freedom rank of #306; its 90% source-sensitivity interval is #90–#480. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is SM-Bench (eq_boundaries, #16 of 84); its weakest is Adversarial Poetry Refusal (AHB self-run) (indiscriminate_weapons_cbrne, #5 of 8).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗longcat-2-0
- Hugging Face ↗meituan-longcat/LongCat-2.0
- OpenRouter ↗meituan/longcat-2.0
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- 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 | #145 / 345 | ↓0.7539 | Source ↗official | |
| Adversarial Poetry Refusal (AHB self-run)child_sexual_exploitation | #5 / 8 | ↓4.348 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)defamation | #6 / 8 | ↓17.39 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)hate | #3 / 8 | ↓5.797 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)indiscriminate_weapons_cbrne | #4 / 8 | ↓7.971 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)intellectual_property | #6 / 8 | ↓10.87 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)non_violent_crimes | #6 / 8 | ↓10.14 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)privacy | #6 / 8 | ↓18.84 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)sex_related_crimes | #6 / 8 | ↓12.32 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)sexual_content | #7 / 8 | ↓15.15 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)specialized_advice | #6 / 8 | ↓6.333 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)suicide_self_harm | #6 / 8 | ↓9.848 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)violent_crimes | #6 / 8 | ↓14.39 | Source ↗self run | |
| SM-Benchadversarial | #45 / 84 | ↑81.46 | Source ↗official | |
| SM-Benchambiguous_interpretation | #69 / 84 | ↑77.98 | Source ↗official | |
| SM-Benchanti_hallucination | #78 / 84 | ↑76.44 | Source ↗official | |
| SM-Bencheq_boundaries | #16 / 84 | ↑70.79 | Source ↗official | |
| SM-Benchoverfit | #38 / 84 | ↑77.6 | 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.