# DeepSeek V4.1 Flash vs Qwen3 Max

> DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 43.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-qwen3-max
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 7 categories and Qwen3 Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 22.0.
- The biggest single-benchmark swing is NYT Connections (extended): 89.6% for DeepSeek V4.1 Flash and 30.1% for Qwen3 Max.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 262K.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 50.3 | 43.5 |
| Rank | 40 | 82 |
| Context | 1M | 262K |
| Input $/M | $0.15 | $1.20 |
| Output $/M | $0.60 | $6 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4.1 Flash: 52.8 (#29)
- Qwen3 Max: 42.4 (#93)

| Benchmark | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1511 | 1456 |
| ALE-Bench | 1,092 | 370.45 |
| LMArena WebDev | 1620 | — |
| SciCode | 51.9% | — |

## Agentic & Tool Use

- DeepSeek V4.1 Flash: —
- Qwen3 Max: —

| Benchmark | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | — | 71.56 |

## Reasoning

- DeepSeek V4.1 Flash: 46.2 (#39)
- Qwen3 Max: 22.0 (#186)

| Benchmark | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| NYT Connections (extended) | 89.6% | 30.1% |
| LMArena Hard Prompts | 1485 | 1448 |
| DTBench | 89.9% | 82.1% |
| LMCA | 47% | 28.3% |
| Epoch Capabilities Index | 155.01 | 142.41 |
| Kagi LLM Benchmark | — | 72.5% |
| CritPt | 14.3% | — |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 5% |
| Surface Evolver Bench | 46.3% | — |

## Math

- DeepSeek V4.1 Flash: 48.4 (#52)
- Qwen3 Max: 37.6 (#94)

| Benchmark | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| LMArena Math | 1493 | 1447 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| ProofBench | 54% | — |
| MATH Level 5 | — | 97.1% |

## Knowledge

- DeepSeek V4.1 Flash: 41.6 (#97)
- Qwen3 Max: 48.1 (#72)

| Benchmark | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1505 | 1457 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |

## Multilingual

- DeepSeek V4.1 Flash: 55.5 (#29)
- Qwen3 Max: 53.9 (#58)

| Benchmark | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1452 | 1429 |
| LMArena Chinese | 1506 | 1479 |
| LMArena French | 1448 | 1450 |
| LMArena Russian | 1473 | 1428 |
| LMArena Spanish | 1499 | 1463 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1397 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.6 (#24)
- Qwen3 Max: 75.0 (#81)

| Benchmark | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1475 | 1420 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#46)
- Qwen3 Max: 41.6 (#129)

| Benchmark | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1476 | 1439 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.8 (#43)
- Qwen3 Max: 62.6 (#72)

| Benchmark | DeepSeek V4.1 Flash | Qwen3 Max |
|---|---|---|
| LMArena Text | 1465 | 1439 |
| LMArena Creative Writing | 1436 | 1401 |
| LMArena Multi-Turn | 1460 | 1446 |
| EQ-Bench Creative Writing | 1540 | — |

## FAQ

### Is DeepSeek V4.1 Flash better than Qwen3 Max?

DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 43.5 on the Noometry Index.

### Which is cheaper, DeepSeek V4.1 Flash or Qwen3 Max?

DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3 Max lists at $1.20 and $6.

### Is DeepSeek V4.1 Flash or Qwen3 Max better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4.1 Flash does, with 1M tokens against 262K.

### How many benchmarks do DeepSeek V4.1 Flash and Qwen3 Max share?

19 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and Qwen3 Max has 33.