# Qwen2.5-Max vs Qwen3.6 Plus

> Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 40.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-max-vs-qwen3-6-plus
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Qwen2.5-Max scores higher in 1 category and Qwen3.6 Plus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 35.3.

## Snapshot

| | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 40.7 | 47.5 |
| Rank | 146 | 62 |
| Context | — | 1M |
| Input $/M | — | $0.50 |
| Output $/M | — | $3 |
| Weights | Proprietary | Proprietary |

## Coding

- Qwen2.5-Max: 41.8 (#117)
- Qwen3.6 Plus: 40.8 (#130)

| Benchmark | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| LMArena Coding | 1359 | 1467 |
| SWE-bench Verified | — | 57.9% |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| LiveBench Coding | 64.4% | — |
| ALE-Bench | — | 670.15 |

## Agentic & Tool Use

- Qwen2.5-Max: —
- Qwen3.6 Plus: —

| Benchmark | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | — | 5,115 |

## Reasoning

- Qwen2.5-Max: 25.6 (#147)
- Qwen3.6 Plus: 29.3 (#93)

| Benchmark | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| LMArena Hard Prompts | 1360 | 1449 |
| Epoch Capabilities Index | 132.53 | 147.65 |
| NYT Connections (extended) | — | 60.3% |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 17% |
| Thematic Generalization | — | 59.5% |
| LiveBench Reasoning | 51.4% | — |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LiveBench Data Analysis | 67.9% | — |
| LMCA | — | 33.1% |
| LiveBench | 62.3% | — |

## Math

- Qwen2.5-Max: 36.9 (#162)
- Qwen3.6 Plus: 51.8 (#54)

| Benchmark | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| LMArena Math | 1369 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| LiveBench Math | 58.4% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |

## Knowledge

- Qwen2.5-Max: 35.3 (#186)
- Qwen3.6 Plus: 56.1 (#45)

| Benchmark | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| LMArena Expert | 1337 | 1454 |
| GPQA Diamond | — | 88.4% |
| SimpleQA Verified | — | 44.1% |
| Confabulations | 21.8% | — |

## Multilingual

- Qwen2.5-Max: 48.1 (#146)
- Qwen3.6 Plus: 53.3 (#70)

| Benchmark | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1352 | 1424 |
| LMArena Chinese | 1382 | 1477 |
| LMArena French | 1396 | 1455 |
| LMArena German | 1350 | 1452 |
| LMArena Japanese | 1300 | 1389 |
| LMArena Korean | 1304 | 1379 |
| LMArena Russian | 1353 | 1434 |
| LMArena Spanish | 1377 | 1432 |

## Instruction Following

- Qwen2.5-Max: 71.3 (#152)
- Qwen3.6 Plus: 75.0 (#74)

| Benchmark | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1335 | 1425 |
| LiveBench Instruction Following | 75.3% | — |

## Long Context

- Qwen2.5-Max: 41.4 (#142)
- Qwen3.6 Plus: 45.2 (#49)

| Benchmark | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1358 | 1439 |
| CL-bench | — | 20.3% |

## Writing & Preference

- Qwen2.5-Max: 55.4 (#146)
- Qwen3.6 Plus: 62.2 (#82)

| Benchmark | Qwen2.5-Max | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1367 | 1437 |
| LMArena Creative Writing | 1339 | 1404 |
| LMArena Multi-Turn | 1364 | 1438 |
| Short-Story Creative Writing | 72.9% | — |
| LiveBench Language | 56.3% | — |

## FAQ

### Is Qwen2.5-Max better than Qwen3.6 Plus?

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 40.7 on the Noometry Index.

### Is Qwen2.5-Max or Qwen3.6 Plus better for coding?

They score almost the same on coding (41.8 vs 40.8); test both on your own repository before choosing.

### How many benchmarks do Qwen2.5-Max and Qwen3.6 Plus share?

18 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Qwen3.6 Plus has 37.