# Qwen2-72B vs Qwen3.6 Plus

> Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-72b-vs-qwen3-6-plus
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3.6 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 21.2.
- The biggest single-benchmark swing is GPQA Diamond: 40.8% for Qwen2-72B and 88.4% for Qwen3.6 Plus.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.0 | 47.5 |
| Rank | 300 | 62 |
| Context | — | 1M |
| Input $/M | — | $0.50 |
| Output $/M | — | $3 |
| Weights | Open | Proprietary |

## Coding

- Qwen2-72B: 29.1 (#310)
- Qwen3.6 Plus: 40.8 (#130)

| Benchmark | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| LMArena Coding | 1196 | 1467 |
| SWE-bench Verified | — | 57.9% |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |
| ALE-Bench | — | 670.15 |

## Agentic & Tool Use

- Qwen2-72B: 17.0 (#146)
- Qwen3.6 Plus: —

| Benchmark | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
| Vending-Bench 2 | — | 5,115 |

## Reasoning

- Qwen2-72B: 23.2 (#181)
- Qwen3.6 Plus: 29.3 (#93)

| Benchmark | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1449 |
| Epoch Capabilities Index | 125.28 | 147.65 |
| 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% |

## Math

- Qwen2-72B: 30.2 (#236)
- Qwen3.6 Plus: 51.8 (#54)

| Benchmark | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| LMArena Math | 1235 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| MATH Level 5 | 39.1% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |

## Knowledge

- Qwen2-72B: 21.2 (#275)
- Qwen3.6 Plus: 56.1 (#45)

| Benchmark | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 40.8% | 88.4% |
| LMArena Expert | 1171 | 1454 |
| SimpleQA Verified | — | 44.1% |
| MMLU | 82.4% | — |

## Multilingual

- Qwen2-72B: 35.9 (#244)
- Qwen3.6 Plus: 53.3 (#70)

| Benchmark | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1176 | 1424 |
| LMArena Chinese | 1240 | 1477 |
| LMArena French | 1170 | 1455 |
| LMArena German | 1151 | 1452 |
| LMArena Japanese | 1111 | 1389 |
| LMArena Korean | 1083 | 1379 |
| LMArena Russian | 1169 | 1434 |
| LMArena Spanish | 1169 | 1432 |

## Instruction Following

- Qwen2-72B: 61.7 (#241)
- Qwen3.6 Plus: 75.0 (#74)

| Benchmark | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1181 | 1425 |

## Long Context

- Qwen2-72B: 36.1 (#235)
- Qwen3.6 Plus: 45.2 (#49)

| Benchmark | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1192 | 1439 |
| CL-bench | — | 20.3% |

## Writing & Preference

- Qwen2-72B: 40.8 (#241)
- Qwen3.6 Plus: 62.2 (#82)

| Benchmark | Qwen2-72B | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1203 | 1437 |
| LMArena Creative Writing | 1181 | 1404 |
| LMArena Multi-Turn | 1196 | 1438 |

## FAQ

### Is Qwen2-72B better than Qwen3.6 Plus?

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 30.0 on the Noometry Index.

### Is Qwen2-72B or Qwen3.6 Plus better for coding?

Qwen3.6 Plus scores higher on coding benchmarks: 40.8 versus 29.1 in the Noometry coding category.

### How many benchmarks do Qwen2-72B and Qwen3.6 Plus share?

19 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3.6 Plus has 37.