# DeepSeek-V2.5 (Sep 2024) vs Qwen3.7 Max

> Qwen3.7 Max is the stronger model overall, scoring 51.5 to 37.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-qwen3-7-max
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Max leads 61.6 to 34.8.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 51.5 |
| Rank | 200 | 42 |
| Context | — | 1M |
| Input $/M | — | $2.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
- Qwen3.7 Max: 50.4 (#45)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1309 | 1498 |
| SWE-bench Verified | — | 77.3% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Agentic & Tool Use

- DeepSeek-V2.5 (Sep 2024): —
- Qwen3.7 Max: 22.1 (#135)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
- Qwen3.7 Max: 49.2 (#38)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1483 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.68 |

## Math

- DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
- Qwen3.7 Max: 62.4 (#32)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1288 | 1490 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
- Qwen3.7 Max: 61.6 (#28)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1266 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
- Qwen3.7 Max: 56.9 (#15)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1273 | 1474 |
| LMArena Chinese | 1318 | 1530 |
| LMArena Russian | 1289 | 1484 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
- Qwen3.7 Max: 76.7 (#38)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1280 | 1460 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
- Qwen3.7 Max: 45.4 (#40)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1301 | 1482 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
- Qwen3.7 Max: 65.0 (#54)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1294 | 1476 |
| LMArena Creative Writing | 1285 | 1449 |
| LMArena Multi-Turn | 1297 | 1481 |
| EQ-Bench 4 | — | 1110 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 37.6 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 31.7 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen3.7 Max share?

12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen3.7 Max has 33.