# DeepSeek V4 Pro vs Qwen2.5 7B Instruct

> DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 1.8× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v4-pro-vs-qwen2-5-7b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 7 categories and Qwen2.5 7B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4 Pro leads 64.6 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.6% for DeepSeek V4 Pro and 2.5% for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $0.43 / $0.87 for DeepSeek V4 Pro.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 131K.

## Snapshot

| | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 54.2 | 28.6 |
| Rank | 28 | 314 |
| Context | 1M | 131K |
| Input $/M | $0.43 | $0.17 |
| Output $/M | $0.87 | $0.70 |
| Weights | Open | Open |

## Coding

- DeepSeek V4 Pro: 52.2 (#31)
- Qwen2.5 7B Instruct: 35.9 (#204)

| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1470 | — |
| BigCodeBench Complete | — | 46.1% |
| ALE-Bench | 1,403 | — |

## Agentic & Tool Use

- DeepSeek V4 Pro: 32.7 (#54)
- Qwen2.5 7B Instruct: 23.5 (#117)

| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| APEX-Agents | 47.3% | — |
| BALROG | — | 7.8% |
| Vending-Bench 2 | 3,285 | — |

## Reasoning

- DeepSeek V4 Pro: 56.4 (#22)
- Qwen2.5 7B Instruct: 14.3 (#317)

| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | 47% | 0% |
| DTBench | 93.9% | 47.7% |
| LMCA | 45.5% | 6.4% |
| Epoch Capabilities Index | 155.39 | 118.44 |
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 43% | — |
| Surface Evolver Bench | 40% | — |
| ForecastBench | 56.1 | — |

## Math

- DeepSeek V4 Pro: 64.6 (#24)
- Qwen2.5 7B Instruct: 11.8 (#300)

| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.6% | 2.5% |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| ProofBench | 50% | — |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1455 | — |

## Knowledge

- DeepSeek V4 Pro: 59.5 (#28)
- Qwen2.5 7B Instruct: 17.0 (#281)

| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 91.7% | 35.5% |
| SimpleQA Verified | 52.9% | — |
| MMLU-Pro | — | 53.9% |
| Vectara Hallucination Rate | 8.6% | — |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1463 | — |
| MMLU | — | 72.9% |

## Multilingual

- DeepSeek V4 Pro: 54.5 (#44)
- Qwen2.5 7B Instruct: —

| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1438 | — |
| LMArena Chinese | 1486 | — |
| LMArena French | 1473 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1448 | — |
| LMArena Korean | 1452 | — |
| LMArena Russian | 1452 | — |
| LMArena Spanish | 1457 | — |

## Instruction Following

- DeepSeek V4 Pro: 76.3 (#44)
- Qwen2.5 7B Instruct: 63.4 (#226)

| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1448 | — |

## Long Context

- DeepSeek V4 Pro: 45.0 (#49)
- Qwen2.5 7B Instruct: —

| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1459 | — |

## Writing & Preference

- DeepSeek V4 Pro: 65.6 (#45)
- Qwen2.5 7B Instruct: 48.8 (#194)

| Benchmark | DeepSeek V4 Pro | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1446 | — |
| EQ-Bench Creative Writing | 1553 | — |
| WildBench | — | 73.1% |
| EQ-Bench 4 | 1166 | — |
| LMArena Multi-Turn | 1467 | — |

## FAQ

### Is DeepSeek V4 Pro better than Qwen2.5 7B Instruct?

DeepSeek V4 Pro is the stronger model overall, scoring 54.2 to 28.6 on the Noometry Index. Qwen2.5 7B Instruct costs 1.8× less per token, which makes it the better buy when DeepSeek V4 Pro's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek V4 Pro or Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; DeepSeek V4 Pro lists at $0.43 and $0.87.

### Is DeepSeek V4 Pro or Qwen2.5 7B Instruct better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.2 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4 Pro does, with 1M tokens against 131K.

### How many benchmarks do DeepSeek V4 Pro and Qwen2.5 7B Instruct share?

6 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Qwen2.5 7B Instruct has 15.