# DeepSeek-V3.1 vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.0 to 42.2 on the Noometry Index. DeepSeek-V3.1 costs 7.1× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.1 to 36.1.
- The biggest single-benchmark swing is LMCA: 24.3% for DeepSeek-V3.1 and 46.2% for Qwen3.8 Max.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.2 | 56.0 |
| Rank | 106 | 21 |
| Context | 164K | 1M |
| Input $/M | $0.25 | $2 |
| Output $/M | $0.95 | $6 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1: 39.8 (#140)
- Qwen3.8 Max: 52.3 (#30)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1417 | 1499 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1671 |
| FrontierSWE | — | 15.8% |
| SciCode | — | 52.9% |
| WeirdML | 38.4% | — |

## Agentic & Tool Use

- DeepSeek-V3.1: —
- Qwen3.8 Max: 42.6 (#17)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- DeepSeek-V3.1: 27.3 (#109)
- Qwen3.8 Max: 53.4 (#26)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1493 |
| DTBench | 82.7% | 92% |
| LMCA | 24.3% | 46.2% |
| Epoch Capabilities Index | 139.92 | 156.69 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| ForecastBench | 58 | — |

## Math

- DeepSeek-V3.1: 36.1 (#125)
- Qwen3.8 Max: 73.1 (#15)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1420 | 1498 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |

## Knowledge

- DeepSeek-V3.1: 43.0 (#86)
- Qwen3.8 Max: 61.7 (#25)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1403 | 1504 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| Vectara Hallucination Rate | 5.5% | — |

## Multimodal

- DeepSeek-V3.1: —
- Qwen3.8 Max: 36.9 (#70)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- DeepSeek-V3.1: 51.8 (#100)
- Qwen3.8 Max: 56.6 (#18)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1400 | 1468 |
| LMArena Chinese | 1470 | 1537 |
| LMArena French | 1447 | 1502 |
| LMArena German | 1412 | 1489 |
| LMArena Japanese | 1374 | 1466 |
| LMArena Korean | 1337 | 1467 |
| LMArena Russian | 1405 | 1478 |
| LMArena Spanish | 1429 | 1495 |

## Instruction Following

- DeepSeek-V3.1: 74.1 (#105)
- Qwen3.8 Max: 77.7 (#19)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1400 | 1478 |

## Long Context

- DeepSeek-V3.1: 36.3 (#227)
- Qwen3.8 Max: 45.5 (#30)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1422 | 1486 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.5 (#93)
- Qwen3.8 Max: 67.0 (#31)

| Benchmark | DeepSeek-V3.1 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1420 | 1480 |
| LMArena Creative Writing | 1401 | 1478 |
| LMArena Multi-Turn | 1408 | 1487 |
| EQ-Bench Creative Writing | 1436 | — |

## FAQ

### Is DeepSeek-V3.1 better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.0 to 42.2 on the Noometry Index. DeepSeek-V3.1 costs 7.1× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek-V3.1 or Qwen3.8 Max?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Qwen3.8 Max lists at $2 and $6.

### Is DeepSeek-V3.1 or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 39.8 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.8 Max does, with 1M tokens against 164K.

### How many benchmarks do DeepSeek-V3.1 and Qwen3.8 Max share?

20 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen3.8 Max has 38.