meituan / longcat family
longcat-flash-thinking-2601
meituan/longcat-flash-thinking-2601
Benchmarks
Where it scores.
General Provisional
72.9
Coding Provisional
65.1
Math Provisional
70.4
Reasoning Provisional
54.7
Normalized 0–100 across indexed models.
Runnable variants
Pick a size.
No recommended variants are indexed for this model.
Raw benchmarks
The inputs.
| Source | Task | Raw | Normalized |
|---|---|---|---|
| ZeroEval | AIME2025 | 99.6 | 99.6 |
| ZeroEval | GPQA | 80.5 | 80.5 |
| ZeroEval | HLE | 25.2 | 25.2 |
| ZeroEval | SWEBenchVerified | 70.0 | 70.0 |
From the Hugging Face model card
About this model.
From the Hugging Face model card