meituan / longcat family
longcat-flash-thinking
meituan/longcat-flash-thinking
Benchmarks
Where it scores.
General Provisional
85.4
Coding Provisional
70.5
Math Provisional
86.5
Reasoning Provisional
86.1
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 | 90.6 | 90.6 |
| ZeroEval | GPQA | 81.5 | 81.5 |
| ZeroEval | SWEBenchVerified | 59.4 | 59.4 |
From the Hugging Face model card
About this model.
From the Hugging Face model card