Longcat Flash Thinking 2601 longcat-flash-thinking-2601
meituan-longcat · longcat
unranked — no quality signals yet
- params
- 561.9B
- arch
- moe
- license
- mit open weights
- released
- Jan 2026
- downloads/30d
- 1.5k
# architecture
- layers
- 28
- d_model
- 6144
- heads
- 64q / 64kv
- head dim
- 96
- experts
- top-0 of 512
- vocab
- 131072
signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.
# why ranked
Overall: provisional — score 74.2 ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.70 | — |
| bench_composite | 0.30 | 74.2 |
benchmark panel evidence:
| complete panel | score (0–100) |
|---|---|
| aime-2025-v1 | 89.0 |
| browsecomp-v1 | 59.4 |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
# benchmarks
# where to run
no known API providers — download the weights from Hugging Face and run them yourself.
source aliases
- llmstats
longcat-flash-thinking-2601