# DeepSeek V4 Pro vs Qwen3.7 Plus

> DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 45.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-pro-vs-qwen3-7-plus
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 8 categories and Qwen3.7 Plus in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 39.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 64.6% for DeepSeek V4 Pro and 34.4% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $0.66 / $1.98 for DeepSeek V4 Pro.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 54.3 | 45.3 |
| Rank | 31 | 72 |
| Context | 1M | 1M |
| Input $/M | $0.66 | $0.40 |
| Output $/M | $1.98 | $1.60 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Pro: 52.4 (#34)
- Qwen3.7 Plus: 36.6 (#206)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| FrontierCode | 28.6% | 10.2% |
| SciCode | 51% | 45.5% |
| LMArena Coding | 1470 | 1473 |
| SWE-bench Verified | 77.6% | — |
| LMArena WebDev | 1582 | — |
| WeirdML | 66.2% | — |
| ALE-Bench | 1,403 | — |

## Agentic & Tool Use

- DeepSeek V4 Pro: 32.8 (#58)
- Qwen3.7 Plus: 21.4 (#138)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| APEX-Agents | 47.3% | — |
| OSWorld 2.0 | — | 2.8% |
| Vending-Bench 2 | 3,285 | — |

## Reasoning

- DeepSeek V4 Pro: 56.5 (#24)
- Qwen3.7 Plus: 39.3 (#59)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 91.3% | 74.8% |
| CritPt | 18% | 9.1% |
| Chess Puzzles | 47% | 24% |
| LMArena Hard Prompts | 1461 | 1460 |
| Mystery Game Puzzles | 43% | 17% |
| DTBench | 93.9% | 84% |
| LMCA | 45.5% | 37.6% |
| Epoch Capabilities Index | 155.31 | 147.37 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| ARC-AGI-1 | 90.5% | — |
| Surface Evolver Bench | 40% | — |
| ForecastBench | 56.1 | — |

## Math

- DeepSeek V4 Pro: 64.8 (#30)
- Qwen3.7 Plus: 50.5 (#56)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | 34.4% |
| OTIS Mock AIME 2024-2025 | 98.6% | 93.3% |
| LMArena Math | 1455 | 1466 |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| ProofBench | 50% | — |

## Knowledge

- DeepSeek V4 Pro: 59.5 (#31)
- Qwen3.7 Plus: 54.9 (#51)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 91.7% | 87.9% |
| LMArena Expert | 1464 | 1467 |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |

## Multimodal

- DeepSeek V4 Pro: —
- Qwen3.7 Plus: 41.8 (#33)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |

## Multilingual

- DeepSeek V4 Pro: 54.4 (#45)
- Qwen3.7 Plus: 54.8 (#38)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1439 | 1445 |
| LMArena Chinese | 1486 | 1510 |
| LMArena French | 1472 | 1473 |
| LMArena German | 1458 | 1471 |
| LMArena Japanese | 1445 | 1413 |
| LMArena Korean | 1447 | 1415 |
| LMArena Russian | 1453 | 1457 |
| LMArena Spanish | 1458 | 1457 |

## Instruction Following

- DeepSeek V4 Pro: 76.1 (#47)
- Qwen3.7 Plus: 75.8 (#52)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1448 | 1440 |

## Long Context

- DeepSeek V4 Pro: 45.0 (#51)
- Qwen3.7 Plus: 44.5 (#65)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1458 | 1455 |
| CL-bench Life | 13.5% | — |

## Writing & Preference

- DeepSeek V4 Pro: 65.5 (#46)
- Qwen3.7 Plus: 64.3 (#56)

| Benchmark | DeepSeek V4 Pro | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1451 | 1455 |
| LMArena Creative Writing | 1446 | 1439 |
| LMArena Multi-Turn | 1467 | 1460 |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |

## FAQ

### Is DeepSeek V4 Pro better than Qwen3.7 Plus?

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 45.3 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Pro or Qwen3.7 Plus?

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; DeepSeek V4 Pro lists at $0.66 and $1.98.

### Is DeepSeek V4 Pro or Qwen3.7 Plus better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 36.6 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do DeepSeek V4 Pro and Qwen3.7 Plus share?

29 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Qwen3.7 Plus has 32.