LongCat
LongCat 2.0
Quality Score36.1
Value Score31.5
Reliability38.3
Cache Discount98%
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.750
- Output
- $2.95
- Cached Input
- $0.015
- Cached Output
- not available
- Cost per task
- $0.121
Capability
- Intelligence
- 34.0
- Coding
- 45.3
- Agentic
- 22.0
- Omniscience
- -23.4
- Correct
- 29.6%
- Blended price
- $0.455
Answer outcomes
Correct 29.6%Incorrect 53.1%Abstained 17.3%
Artificial Analysis benchmarks
- GDPval-AA v2
- 27%
- τ³-Banking
- 13%
- Terminal-Bench v2.1
- 50%
- SciCode
- 35%
- Humanity’s Last Exam
- 34%
- GPQA Diamond
- 78%
- CritPt
- 3%
- AA-Omniscience
- 38%
- AA-LCR
- 63%
Similar models
- LongCat Flash LiteLongCatQuality Score 12.2Value Score not available
- A.X-K2SK TelecomQuality Score 35.9Value Score not available
- Qwen3.5 397B A17B (Reasoning)AlibabaQuality Score 35.0Value Score 29.3
- Qwen3.6 27B (Reasoning)AlibabaQuality Score 36.1Value Score 29.4
- Ling 3.0 FlashInclusionAIQuality Score 36.0Value Score 38.8
- Muse Glimmer (high)MetaQuality Score 34.2Value Score 34.0