# DeepSeek-V3.1-Terminus vs Qwen Max

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 34.4 on the Noometry Index.

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

## Summary

- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Qwen Max in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 35.7 to 21.0.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 33K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1-Terminus | Qwen Max |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.6 | 34.4 |
| Rank | 96 | 226 |
| Context | 164K | 33K |
| Input $/M | $0.30 | $1.60 |
| Output $/M | $1 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- Qwen Max: 30.3 (#288)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen Max |
|---|---|---|
| LMArena Coding | 1426 | 1288 |
| Aider Polyglot | — | 21.8% |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- Qwen Max: 24.1 (#154)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1270 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- Qwen Max: 21.0 (#272)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen Max |
|---|---|---|
| LMArena Math | 1402 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Qwen Max: 30.3 (#222)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen Max |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| LMArena Expert | — | 1248 |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- Qwen Max: 42.0 (#197)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen Max |
|---|---|---|
| LMArena Non-English | 1407 | 1263 |
| LMArena Russian | 1434 | 1274 |
| LMArena Chinese | — | 1254 |
| LMArena French | — | 1329 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1141 |
| LMArena Spanish | — | 1290 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- Qwen Max: 66.7 (#203)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1406 | 1262 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- Qwen Max: 39.4 (#175)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1426 | 1289 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- Qwen Max: 48.0 (#200)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen Max |
|---|---|---|
| LMArena Text | 1420 | 1282 |
| LMArena Creative Writing | 1404 | 1248 |
| LMArena Multi-Turn | 1411 | 1277 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Qwen Max?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 34.4 on the Noometry Index.

### Which is cheaper, DeepSeek-V3.1-Terminus or Qwen Max?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is DeepSeek-V3.1-Terminus or Qwen Max better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 30.3 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek-V3.1-Terminus does, with 164K tokens against 33K.

### How many benchmarks do DeepSeek-V3.1-Terminus and Qwen Max share?

10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen Max has 23.