# Qwen3.6 Plus vs Qwen3 Max

> Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 43.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-6-plus-vs-qwen3-max
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Qwen3.6 Plus scores higher in 5 categories and Qwen3 Max in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Plus leads 50.6 to 37.6.
- The biggest single-benchmark swing is NYT Connections (extended): 60.3% for Qwen3.6 Plus and 30.1% for Qwen3 Max.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3.6 Plus accepts more context: 1M tokens versus 262K.

## Snapshot

| | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 47.3 | 43.5 |
| Rank | 54 | 82 |
| Context | 1M | 262K |
| Input $/M | $0.50 | $1.20 |
| Output $/M | $3 | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Qwen3.6 Plus: 40.6 (#125)
- Qwen3 Max: 42.4 (#93)

| Benchmark | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1467 | 1456 |
| ALE-Bench | 670.15 | 370.45 |
| SWE-bench Verified | 57.9% | — |
| LMArena WebDev | 1461 | — |
| SciCode | 40.7% | — |

## Agentic & Tool Use

- Qwen3.6 Plus: —
- Qwen3 Max: —

| Benchmark | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | 5,115 | 71.56 |

## Reasoning

- Qwen3.6 Plus: 28.5 (#89)
- Qwen3 Max: 22.0 (#186)

| Benchmark | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| NYT Connections (extended) | 60.3% | 30.1% |
| Chess Puzzles | 17% | 4% |
| LMArena Hard Prompts | 1449 | 1448 |
| Mystery Game Puzzles | 12% | 5% |
| DTBench | 81.9% | 82.1% |
| LMCA | 33.1% | 28.3% |
| Epoch Capabilities Index | 147.67 | 142.41 |
| Kagi LLM Benchmark | — | 72.5% |
| CritPt | 2.9% | — |
| Thematic Generalization | 59.5% | — |

## Math

- Qwen3.6 Plus: 50.6 (#44)
- Qwen3 Max: 37.6 (#94)

| Benchmark | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 38.2% | 18.9% |
| OTIS Mock AIME 2024-2025 | 93.3% | 73.3% |
| LMArena Math | 1450 | 1447 |
| MATH Level 5 | — | 97.1% |
| FrontierMath (Feb 2025 set) | 26.2% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |

## Knowledge

- Qwen3.6 Plus: 56.1 (#40)
- Qwen3 Max: 48.1 (#72)

| Benchmark | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 88.4% | 72.6% |
| SimpleQA Verified | 44.1% | 48.7% |
| LMArena Expert | 1456 | 1457 |

## Multilingual

- Qwen3.6 Plus: 53.5 (#66)
- Qwen3 Max: 53.9 (#58)

| Benchmark | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1424 | 1429 |
| LMArena Chinese | 1478 | 1479 |
| LMArena French | 1454 | 1450 |
| LMArena German | 1451 | 1463 |
| LMArena Japanese | 1389 | 1399 |
| LMArena Korean | 1381 | 1397 |
| LMArena Russian | 1434 | 1428 |
| LMArena Spanish | 1432 | 1463 |

## Instruction Following

- Qwen3.6 Plus: 75.2 (#70)
- Qwen3 Max: 75.0 (#81)

| Benchmark | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1425 | 1420 |

## Long Context

- Qwen3.6 Plus: 45.1 (#48)
- Qwen3 Max: 41.6 (#129)

| Benchmark | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| CL-bench | 20.3% | 14.5% |
| LMArena Longer Query | 1440 | 1439 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Qwen3.6 Plus: 62.4 (#78)
- Qwen3 Max: 62.6 (#72)

| Benchmark | Qwen3.6 Plus | Qwen3 Max |
|---|---|---|
| LMArena Text | 1437 | 1439 |
| LMArena Creative Writing | 1405 | 1401 |
| LMArena Multi-Turn | 1438 | 1446 |

## FAQ

### Is Qwen3.6 Plus better than Qwen3 Max?

Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 43.5 on the Noometry Index.

### Which is cheaper, Qwen3.6 Plus or Qwen3 Max?

Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Qwen3 Max lists at $1.20 and $6.

### Is Qwen3.6 Plus or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 42.4 versus 40.6 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.6 Plus does, with 1M tokens against 262K.

### How many benchmarks do Qwen3.6 Plus and Qwen3 Max share?

30 benchmarks have published results for both models. Qwen3.6 Plus has 37 scored results on Noometry and Qwen3 Max has 33.