# DeepSeek V4.1 Flash vs Qwen2.5-Max

> DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 40.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 24.6.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4.1 Flash | Qwen2.5-Max |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 50.3 | 40.1 |
| Rank | 40 | 142 |
| Context | 1M | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4.1 Flash: 52.8 (#29)
- Qwen2.5-Max: 41.2 (#118)

| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1511 | 1359 |
| LMArena WebDev | 1620 | — |
| SciCode | 51.9% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 1,092 | — |

## Reasoning

- DeepSeek V4.1 Flash: 46.2 (#39)
- Qwen2.5-Max: 24.6 (#144)

| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1360 |
| Epoch Capabilities Index | 155.01 | 132.54 |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 89.9% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| LiveBench | — | 62.3% |

## Math

- DeepSeek V4.1 Flash: 48.4 (#52)
- Qwen2.5-Max: 34.3 (#162)

| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1493 | 1369 |
| ProofBench | 54% | — |
| LiveBench Math | — | 58.4% |

## Knowledge

- DeepSeek V4.1 Flash: 41.6 (#97)
- Qwen2.5-Max: 34.8 (#181)

| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1505 | 1337 |
| Confabulations | — | 21.8% |

## Multilingual

- DeepSeek V4.1 Flash: 55.5 (#29)
- Qwen2.5-Max: 48.3 (#140)

| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1452 | 1352 |
| LMArena Chinese | 1506 | 1382 |
| LMArena French | 1448 | 1396 |
| LMArena Russian | 1473 | 1353 |
| LMArena Spanish | 1499 | 1377 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1299 |
| LMArena Korean | — | 1304 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.6 (#24)
- Qwen2.5-Max: 71.5 (#147)

| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1475 | 1335 |
| LiveBench Instruction Following | — | 75.3% |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#46)
- Qwen2.5-Max: 41.3 (#137)

| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1476 | 1358 |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.8 (#43)
- Qwen2.5-Max: 55.6 (#141)

| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1465 | 1367 |
| LMArena Creative Writing | 1436 | 1339 |
| LMArena Multi-Turn | 1460 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1540 | — |
| LiveBench Language | — | 56.3% |

## FAQ

### Is DeepSeek V4.1 Flash better than Qwen2.5-Max?

DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 40.1 on the Noometry Index.

### Is DeepSeek V4.1 Flash or Qwen2.5-Max better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 41.2 in the Noometry coding category.

### How many benchmarks do DeepSeek V4.1 Flash and Qwen2.5-Max share?

15 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and Qwen2.5-Max has 27.