# Qwen3.6 Plus vs Qwen3-Coder 480B-A35B Instruct

> Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 38.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-6-plus-vs-qwen3-coder-480b-a35b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Qwen3.6 Plus scores higher in 8 categories and Qwen3-Coder 480B-A35B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 37.0.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3.6 Plus accepts more context: 1M tokens versus 262K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 47.5 | 38.1 |
| Rank | 62 | 190 |
| Context | 1M | 262K |
| Input $/M | $0.50 | $1.50 |
| Output $/M | $3 | $7.50 |
| Weights | Proprietary | Open |

## Coding

- Qwen3.6 Plus: 40.8 (#130)
- Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)

| Benchmark | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena WebDev | 1461 | 1275 |
| LMArena Coding | 1467 | 1412 |
| ALE-Bench | 670.15 | 461.45 |
| SWE-bench Verified | 57.9% | — |
| SWE-bench Verified (bash only) | — | 55.4% |
| SciCode | 40.7% | — |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| AlgoTune | — | 1.44 |

## Agentic & Tool Use

- Qwen3.6 Plus: —
- Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)

| Benchmark | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| Vending-Bench 2 | 5,115 | — |

## Reasoning

- Qwen3.6 Plus: 29.3 (#93)
- Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)

| Benchmark | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| NYT Connections (extended) | 60.3% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 17% | — |
| Thematic Generalization | 59.5% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 81.9% | — |
| LMCA | 33.1% | — |
| Epoch Capabilities Index | 147.65 | — |

## Math

- Qwen3.6 Plus: 51.8 (#54)
- Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)

| Benchmark | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1450 | 1365 |
| FrontierMath (Tiers 1-3) | 38.2% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| FrontierMath (Feb 2025 set) | 26.2% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |

## Knowledge

- Qwen3.6 Plus: 56.1 (#45)
- Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)

| Benchmark | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1454 | 1338 |
| GPQA Diamond | 88.4% | — |
| SimpleQA Verified | 44.1% | — |

## Multilingual

- Qwen3.6 Plus: 53.3 (#70)
- Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)

| Benchmark | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1424 | 1346 |
| LMArena Chinese | 1477 | 1357 |
| LMArena French | 1455 | 1398 |
| LMArena German | 1452 | 1325 |
| LMArena Japanese | 1389 | 1310 |
| LMArena Korean | 1379 | 1305 |
| LMArena Russian | 1434 | 1366 |
| LMArena Spanish | 1432 | 1360 |

## Instruction Following

- Qwen3.6 Plus: 75.0 (#74)
- Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)

| Benchmark | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1425 | 1355 |

## Long Context

- Qwen3.6 Plus: 45.2 (#49)
- Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)

| Benchmark | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1439 | 1378 |
| CL-bench | 20.3% | — |

## Writing & Preference

- Qwen3.6 Plus: 62.2 (#82)
- Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)

| Benchmark | Qwen3.6 Plus | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1437 | 1357 |
| LMArena Creative Writing | 1404 | 1333 |
| LMArena Multi-Turn | 1438 | 1365 |

## FAQ

### Is Qwen3.6 Plus better than Qwen3-Coder 480B-A35B Instruct?

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 38.1 on the Noometry Index.

### Which is cheaper, Qwen3.6 Plus or Qwen3-Coder 480B-A35B Instruct?

Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.

### Is Qwen3.6 Plus or Qwen3-Coder 480B-A35B Instruct better for coding?

Qwen3.6 Plus scores higher on coding benchmarks: 40.8 versus 35.5 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-Coder 480B-A35B Instruct share?

19 benchmarks have published results for both models. Qwen3.6 Plus has 37 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.