Meituan model product
LongCat-Flash-Thinking-2601 is an upgraded version of LongCat-Flash-Thinking with 560B total parameters (MoE, ~27B activated). It achieves open-source SOTA performance on core evaluation benchmarks including Agentic Search, Agentic Tool Use, and Tool-Integrated Reasoning (TIR). Features Heavy Thinking mode that contributes +4-6 points on demanding agentic reasoning benchmarks. Mid-training with structured agentic trajectories improves pass@k by up to +12 points, and context management yields +17.5 improvement.
Updated Aug 10, 2026. Default version: LongCat-Flash-Thinking-2601
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version LongCat-Flash-Thinking-2601.
| Tau2 Airline | 0.8 | 1 | 23 | 100.0% | C | |
| Tau2 Telecom | 1.0 | 2 | 35 | 97.1% | C | |
| BrowseComp-zh | 0.7 | 4 | 13 | 75.0% | C | |
| Tau2 Retail | 0.9 | 4 | 26 | 88.0% | C | |
| LiveCodeBench | 0.8 | 6 | 73 | 93.1% | C | |
| AIME 2025 | 1.0 | 9 | 114 | 92.9% | C | |
| IMO-AnswerBench | 0.8 | 18 | 19 | 5.6% | C | |
| BrowseComp | 0.6 | 38 | 58 | 35.1% | C | |
| Humanity's Last Exam | 0.3 | 48 | 92 | 48.4% | C | |
| SWE-Bench Verified | 0.7 | 58 | 104 | 44.7% | C | |
| GPQA | 0.8 | 85 | 233 | 63.8% | C |
Preference and agent-evaluation signals from published Arena datasets.
The default version has no published Arena rows, or its source alias has not been resolved.
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
The default version has no provider offering with current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| LongCat-Flash-Thinking-2601 | 61.2 | 560B | 128K | 128K | No | MIT | |
| LongCat-Flash-Thinking | N/A | 560B | 128K | 128K | No | MIT |
A concise description based on the published model registry.
LongCat-Flash-Thinking-2601 is an upgraded version of LongCat-Flash-Thinking with 560B total parameters (MoE, ~27B activated). It achieves open-source SOTA performance on core evaluation benchmarks including Agentic Search, Agentic Tool Use, and Tool-Integrated Reasoning (TIR). Features Heavy Thinking mode that contributes +4-6 points on demanding agentic reasoning benchmarks. Mid-training with structured agentic trajectories improves pass@k by up to +12 points, and context management yields +17.5 improvement.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about LongCat Flash Thinking.
LongCat Flash Thinking's default version was released on Jan 14, 2026.
No official standard PAYG price is currently available for LongCat Flash Thinking.
LongCat Flash Thinking is published under Meituan in the model registry.
The default version has a 128K token context window.
No. The default version is not marked as having publicly available weights.
No published provider offering is currently linked to the default version.
Nearby ranked alternatives include GLM 4.5, o3 mini, Qwen3.5 122B A10B.