# Qwen2.5-Max vs Qwen3.5-Flash

> Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 40.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen2-5-max-vs-qwen3-5-flash
- 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 Qwen3.5-Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5-Flash leads 33.7 to 25.6.

## Snapshot

| | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 40.7 | 42.5 |
| Rank | 146 | 112 |
| Context | — | 1M |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Qwen2.5-Max: 41.8 (#117)
- Qwen3.5-Flash: 34.2 (#242)

| Benchmark | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1359 | 1412 |
| LMArena WebDev | — | 1244 |
| LiveBench Coding | 64.4% | — |
| ALE-Bench | — | 221.8 |

## Agentic & Tool Use

- Qwen2.5-Max: —
- Qwen3.5-Flash: —

| Benchmark | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | — | 462.69 |

## Reasoning

- Qwen2.5-Max: 25.6 (#147)
- Qwen3.5-Flash: 33.7 (#72)

| Benchmark | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| LMArena Hard Prompts | 1360 | 1403 |
| Epoch Capabilities Index | 132.53 | 143.98 |
| Chess Puzzles | — | 21% |
| LiveBench Reasoning | 51.4% | — |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 82.9% |
| LiveBench Data Analysis | 67.9% | — |
| LMCA | — | 29.1% |
| LiveBench | 62.3% | — |

## Math

- Qwen2.5-Max: 36.9 (#162)
- Qwen3.5-Flash: 37.4 (#158)

| Benchmark | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| LMArena Math | 1369 | 1407 |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| LiveBench Math | 58.4% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Qwen2.5-Max: 35.3 (#186)
- Qwen3.5-Flash: 43.2 (#93)

| Benchmark | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| LMArena Expert | 1337 | 1407 |
| GPQA Diamond | — | 82.3% |
| SimpleQA Verified | — | 20.3% |
| Confabulations | 21.8% | — |
| Vectara Hallucination Rate | — | 10.5% |

## Multilingual

- Qwen2.5-Max: 48.1 (#146)
- Qwen3.5-Flash: 50.5 (#121)

| Benchmark | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1352 | 1385 |
| LMArena Chinese | 1382 | 1446 |
| LMArena French | 1396 | 1412 |
| LMArena German | 1350 | 1390 |
| LMArena Japanese | 1300 | 1368 |
| LMArena Korean | 1304 | 1344 |
| LMArena Russian | 1353 | 1379 |
| LMArena Spanish | 1377 | 1400 |

## Instruction Following

- Qwen2.5-Max: 71.3 (#152)
- Qwen3.5-Flash: 72.6 (#139)

| Benchmark | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1335 | 1374 |
| LiveBench Instruction Following | 75.3% | — |

## Long Context

- Qwen2.5-Max: 41.4 (#142)
- Qwen3.5-Flash: 42.4 (#124)

| Benchmark | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1358 | 1392 |

## Writing & Preference

- Qwen2.5-Max: 55.4 (#146)
- Qwen3.5-Flash: 57.9 (#122)

| Benchmark | Qwen2.5-Max | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1367 | 1397 |
| LMArena Creative Writing | 1339 | 1343 |
| LMArena Multi-Turn | 1364 | 1393 |
| Short-Story Creative Writing | 72.9% | — |
| LiveBench Language | 56.3% | — |

## FAQ

### Is Qwen2.5-Max better than Qwen3.5-Flash?

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 40.7 on the Noometry Index.

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

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 34.2 in the Noometry coding category.

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

18 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Qwen3.5-Flash has 32.