Developer
Meituan
5 indexed models; 1 currently meet the evidence threshold for the overall ranking. Together they have results from 6 evaluations.
Models by Meituan
| Model | Evals | Components | Rank | Release date |
|---|---|---|---|---|
| Longcat 2.0 | 3 | 5/7 | 130 | 2026-07-05 |
| Evocua 32B | 1 | 1/7 | — | 2026-01-07 |
| Evocua 8B | 1 | 1/7 | — | 2026-01-13 |
| Longcat Flash Chat | 2 | 4/7 | — | 2025-08-29 |
| Longcat Flash Lite | 1 | 1/7 | — | 2026-01-28 |
Evaluations covering Meituan models (6)
AA-Omniscience · Adversarial Poetry Refusal (AHB self-run) · Arena Factuality — Text Arena (factuality-only weighting) · AutoElicit Transferability · LiveSecBench · SM-Bench