# DeepSeek-V3.1-Terminus vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 6.6× 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-terminus-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and Qwen3.8 Max in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 38.5.
- The biggest single-benchmark swing is CritPt: 1.7% for DeepSeek-V3.1-Terminus and 20% for Qwen3.8 Max.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 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-Terminus has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 43.1 | 56.8 |
| Rank | 97 | 22 |
| Context | 164K | 1M |
| Input $/M | $0.27 | $2 |
| Output $/M | $1 | $6 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1-Terminus: 42.0 (#113)
- Qwen3.8 Max: 53.5 (#29)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| SciCode | 40.6% | 53.2% |
| LMArena Coding | 1426 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| ALE-Bench | 745.17 | — |

## Agentic & Tool Use

- DeepSeek-V3.1-Terminus: —
- Qwen3.8 Max: 45.4 (#14)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- DeepSeek-V3.1-Terminus: 26.4 (#133)
- Qwen3.8 Max: 54.4 (#26)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| CritPt | 1.7% | 20% |
| LMArena Hard Prompts | 1426 | 1496 |
| DTBench | 81.3% | 92% |
| LMCA | 28.6% | 46.2% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 88.3% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| Epoch Capabilities Index | — | 156.41 |

## Math

- DeepSeek-V3.1-Terminus: 38.5 (#137)
- Qwen3.8 Max: 73.2 (#20)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1402 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Qwen3.8 Max: 61.7 (#27)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1507 |

## Multimodal

- DeepSeek-V3.1-Terminus: —
- Qwen3.8 Max: 37.2 (#75)

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

## Multilingual

- DeepSeek-V3.1-Terminus: 52.1 (#92)
- Qwen3.8 Max: 56.7 (#18)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1407 | 1472 |
| LMArena Russian | 1436 | 1481 |
| LMArena Chinese | — | 1538 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Spanish | — | 1492 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.0 (#106)
- Qwen3.8 Max: 77.6 (#17)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1404 | 1479 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.4 (#97)
- Qwen3.8 Max: 45.6 (#31)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1421 | 1489 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.0 (#92)
- Qwen3.8 Max: 67.1 (#30)

| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1419 | 1483 |
| LMArena Creative Writing | 1403 | 1479 |
| LMArena Multi-Turn | 1411 | 1489 |

## FAQ

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

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 6.6× 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-Terminus or Qwen3.8 Max?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Qwen3.8 Max lists at $2 and $6.

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

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 42.0 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-Terminus and Qwen3.8 Max share?

14 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen3.8 Max has 39.