LongCat Flash Lite: benchmark results
Meituan LongCat's lite flash tier: 68.5B MoE with ~3B active params and a 256K context (early 2026). Provider: Meituan. Released 2026-01-29. Access: Open.
Unified ELO 1531 ± 1, rank #540 of 1392 rated models, from 37 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 79.53 | Accuracy (%) | 69.7 |
| ZeroEval MATH-500 | 96.8 | MATH-500 Score | 69.4 |
| AA Omniscience - Software Engineering (SWE) - Dart | 18 | Accuracy (%) | 51.5 |
| Artificial Analysis Intelligence Index | 11.18 | Intelligence Index | 50 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 16 | Accuracy (%) | 47.8 |
| AA IFBench | 43.06 | Accuracy (%) | 46.3 |
| AA Omniscience - Software Engineering (SWE) - Julia | 8 | Accuracy (%) | 46.1 |
| AA Terminal-Bench Hard | 10.61 | Accuracy (%) | 45.1 |
| LLM Stats Score | 18.91 | LLM Stats Score (conservative rating) | 43.9 |
| AA Omniscience - Software Engineering (SWE) - PHP | 18 | Accuracy (%) | 43 |
| BenchmarkList ECI | 104.41 | Capability Index (ECI) | 42.1 |
| LLM Stats (CMMLU) | 82.48 | Score (%) | 40 |
Interactive version: theaggregate.ai/model?slug=longcat-flash-lite · How It Works · Data refreshed daily, snapshot 2026-09-05.