# DeepSeek V4 Pro vs Qwen Max

> DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 34.7 on the Noometry Index.

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

## Summary

- They share 19 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and Qwen Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.8 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.6% for DeepSeek V4 Pro and 16.1% for Qwen Max.
- DeepSeek V4 Pro is cheaper at $0.66 / $1.98 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 33K.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 54.3 | 34.7 |
| Rank | 31 | 230 |
| Context | 1M | 33K |
| Input $/M | $0.66 | $1.60 |
| Output $/M | $1.98 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Pro: 52.4 (#34)
- Qwen Max: 30.7 (#292)

| Benchmark | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| LMArena Coding | 1470 | 1288 |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |

## Agentic & Tool Use

- DeepSeek V4 Pro: 32.8 (#58)
- Qwen Max: —

| Benchmark | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |

## Reasoning

- DeepSeek V4 Pro: 56.5 (#24)
- Qwen Max: 25.1 (#151)

| Benchmark | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1269 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |

## Math

- DeepSeek V4 Pro: 64.8 (#30)
- Qwen Max: 22.3 (#276)

| Benchmark | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.6% | 16.1% |
| LMArena Math | 1455 | 1275 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| ProofBench | 50% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- DeepSeek V4 Pro: 59.5 (#31)
- Qwen Max: 30.3 (#228)

| Benchmark | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| GPQA Diamond | 91.7% | 56.1% |
| LMArena Expert | 1464 | 1248 |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |

## Multilingual

- DeepSeek V4 Pro: 54.4 (#45)
- Qwen Max: 41.8 (#202)

| Benchmark | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| LMArena Non-English | 1439 | 1263 |
| LMArena Chinese | 1486 | 1254 |
| LMArena French | 1472 | 1330 |
| LMArena German | 1458 | 1254 |
| LMArena Japanese | 1445 | 1205 |
| LMArena Korean | 1447 | 1142 |
| LMArena Russian | 1453 | 1274 |
| LMArena Spanish | 1458 | 1290 |

## Instruction Following

- DeepSeek V4 Pro: 76.1 (#47)
- Qwen Max: 66.5 (#208)

| Benchmark | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1448 | 1262 |

## Long Context

- DeepSeek V4 Pro: 45.0 (#51)
- Qwen Max: 39.4 (#180)

| Benchmark | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1458 | 1288 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench Life | 13.5% | — |

## Writing & Preference

- DeepSeek V4 Pro: 65.5 (#46)
- Qwen Max: 47.8 (#205)

| Benchmark | DeepSeek V4 Pro | Qwen Max |
|---|---|---|
| LMArena Text | 1451 | 1282 |
| LMArena Creative Writing | 1446 | 1248 |
| LMArena Multi-Turn | 1467 | 1277 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |

## FAQ

### Is DeepSeek V4 Pro better than Qwen Max?

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 34.7 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Pro or Qwen Max?

DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is DeepSeek V4 Pro or Qwen Max better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 30.7 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4 Pro does, with 1M tokens against 33K.

### How many benchmarks do DeepSeek V4 Pro and Qwen Max share?

19 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Qwen Max has 23.