# Longcat Flash Chat vs Qwen2.5 72B Instruct

> Longcat Flash Chat is the stronger model overall, scoring 41.5 to 31.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/longcat-flash-chat-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Longcat Flash Chat scores higher in 7 categories and Qwen2.5 72B Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Longcat Flash Chat leads 36.6 to 18.1.

## Snapshot

| | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Meituan | Alibaba (Qwen) |
| Noometry Index | 41.5 | 31.5 |
| Rank | 121 | 259 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Open | Open |

## Coding

- Longcat Flash Chat: 42.9 (#85)
- Qwen2.5 72B Instruct: 32.8 (#256)

| Benchmark | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1471 | 1293 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Longcat Flash Chat: —
- Qwen2.5 72B Instruct: 22.0 (#124)

| Benchmark | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Longcat Flash Chat: 18.3 (#267)
- Qwen2.5 72B Instruct: 21.4 (#197)

| Benchmark | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1271 |
| Kagi LLM Benchmark | 43.9% | — |
| NYT Connections (extended) | 17.7% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129.01 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Longcat Flash Chat: 36.6 (#107)
- Qwen2.5 72B Instruct: 18.1 (#281)

| Benchmark | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1441 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Longcat Flash Chat: 40.0 (#111)
- Qwen2.5 72B Instruct: 26.9 (#247)

| Benchmark | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1454 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Longcat Flash Chat: 52.1 (#95)
- Qwen2.5 72B Instruct: 41.2 (#208)

| Benchmark | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1404 | 1252 |
| LMArena Chinese | 1465 | 1272 |
| LMArena French | 1457 | 1279 |
| LMArena German | 1409 | 1234 |
| LMArena Japanese | 1373 | 1180 |
| LMArena Korean | 1372 | 1188 |
| LMArena Russian | 1396 | 1264 |
| LMArena Spanish | 1445 | 1255 |

## Instruction Following

- Longcat Flash Chat: 74.6 (#92)
- Qwen2.5 72B Instruct: 65.7 (#216)

| Benchmark | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1411 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Longcat Flash Chat: 43.5 (#89)
- Qwen2.5 72B Instruct: 38.9 (#183)

| Benchmark | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1425 | 1282 |

## Writing & Preference

- Longcat Flash Chat: 61.2 (#88)
- Qwen2.5 72B Instruct: 46.9 (#210)

| Benchmark | Longcat Flash Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1427 | 1269 |
| LMArena Creative Writing | 1388 | 1221 |
| LMArena Multi-Turn | 1418 | 1272 |
| WildBench | — | 80.2% |

## FAQ

### Is Longcat Flash Chat better than Qwen2.5 72B Instruct?

Longcat Flash Chat is the stronger model overall, scoring 41.5 to 31.5 on the Noometry Index.

### Is Longcat Flash Chat or Qwen2.5 72B Instruct better for coding?

Longcat Flash Chat scores higher on coding benchmarks: 42.9 versus 32.8 in the Noometry coding category.

### How many benchmarks do Longcat Flash Chat and Qwen2.5 72B Instruct share?

17 benchmarks have published results for both models. Longcat Flash Chat has 19 scored results on Noometry and Qwen2.5 72B Instruct has 43.