# Qwen Max vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 34.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen-max-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Qwen Max 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 73.2 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.1% for Qwen Max and 100% for Qwen3.8 Max.
- Qwen Max is cheaper at $1.60 / $6.40 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 33K.

## Snapshot

| | Qwen Max | Qwen3.8 Max |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 34.7 | 56.8 |
| Rank | 230 | 22 |
| Context | 33K | 1M |
| Input $/M | $1.60 | $2 |
| Output $/M | $6.40 | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Qwen Max: 30.7 (#292)
- Qwen3.8 Max: 53.5 (#29)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1288 | 1502 |
| DeepSWE | — | 57.5% |
| Aider Polyglot | 21.8% | — |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |

## Agentic & Tool Use

- Qwen Max: —
- Qwen3.8 Max: 45.4 (#14)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- Qwen Max: 25.1 (#151)
- Qwen3.8 Max: 54.4 (#26)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1496 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |

## Math

- Qwen Max: 22.3 (#276)
- Qwen3.8 Max: 73.2 (#20)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.1% | 100% |
| LMArena Math | 1275 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| MATH Level 5 | 67.2% | — |
| FrontierMath (Feb 2025 set) | 1% | — |

## Knowledge

- Qwen Max: 30.3 (#228)
- Qwen3.8 Max: 61.7 (#27)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 56.1% | 92.7% |
| LMArena Expert | 1248 | 1507 |
| SimpleQA Verified | — | 47.3% |

## Multimodal

- Qwen Max: —
- Qwen3.8 Max: 37.2 (#75)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- Qwen Max: 41.8 (#202)
- Qwen3.8 Max: 56.7 (#18)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1263 | 1472 |
| LMArena Chinese | 1254 | 1538 |
| LMArena French | 1330 | 1503 |
| LMArena German | 1254 | 1483 |
| LMArena Japanese | 1205 | 1467 |
| LMArena Korean | 1142 | 1461 |
| LMArena Russian | 1274 | 1481 |
| LMArena Spanish | 1290 | 1492 |

## Instruction Following

- Qwen Max: 66.5 (#208)
- Qwen3.8 Max: 77.6 (#17)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1262 | 1479 |

## Long Context

- Qwen Max: 39.4 (#180)
- Qwen3.8 Max: 45.6 (#31)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1288 | 1489 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- Qwen Max: 47.8 (#205)
- Qwen3.8 Max: 67.1 (#30)

| Benchmark | Qwen Max | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1282 | 1483 |
| LMArena Creative Writing | 1248 | 1479 |
| LMArena Multi-Turn | 1277 | 1489 |

## FAQ

### Is Qwen Max better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 34.7 on the Noometry Index.

### Which is cheaper, Qwen Max or Qwen3.8 Max?

Qwen Max is cheaper. It lists at $1.60 per million input tokens and $6.40 per million output tokens; Qwen3.8 Max lists at $2 and $6.

### Is Qwen Max or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 30.7 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.8 Max does, with 1M tokens against 33K.

### How many benchmarks do Qwen Max and Qwen3.8 Max share?

19 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Qwen3.8 Max has 39.