# Qwen2.5-Coder-32B vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.0 to 32.9 on the Noometry Index. Qwen2.5-Coder-32B costs 4.0× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/qwen2-5-coder-32b-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Qwen2.5-Coder-32B scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.1 to 30.8.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max accepts more context: 1M tokens versus 33K.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

## Snapshot

| | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 32.9 | 56.0 |
| Rank | 239 | 21 |
| Context | 33K | 1M |
| Input $/M | $0.66 | $2 |
| Output $/M | $1 | $6 |
| Weights | Open | Proprietary |

## Coding

- Qwen2.5-Coder-32B: 22.4 (#328)
- Qwen3.8 Max: 52.3 (#30)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1276 | 1499 |
| DeepSWE | — | 57.5% |
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| LMArena WebDev | — | 1671 |
| FrontierSWE | — | 15.8% |
| SciCode | — | 52.9% |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| BigCodeBench Complete | 58% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |

## Agentic & Tool Use

- Qwen2.5-Coder-32B: —
- Qwen3.8 Max: 42.6 (#17)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- Qwen2.5-Coder-32B: 20.4 (#220)
- Qwen3.8 Max: 53.4 (#26)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1493 |
| Epoch Capabilities Index | 119.41 | 156.69 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| LiveBench Reasoning | 42.1% | — |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LiveBench Data Analysis | 49.9% | — |
| LMCA | — | 46.2% |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |

## Math

- Qwen2.5-Coder-32B: 30.8 (#203)
- Qwen3.8 Max: 73.1 (#15)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1251 | 1498 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| LiveBench Math | 46.6% | — |
| GSM8K | 93% | — |

## Knowledge

- Qwen2.5-Coder-32B: 32.9 (#200)
- Qwen3.8 Max: 61.7 (#25)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1221 | 1504 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |

## Multimodal

- Qwen2.5-Coder-32B: —
- Qwen3.8 Max: 36.9 (#70)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- Qwen2.5-Coder-32B: 38.0 (#230)
- Qwen3.8 Max: 56.6 (#18)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1205 | 1468 |
| LMArena Chinese | 1222 | 1537 |
| LMArena Russian | 1228 | 1478 |
| LMArena French | — | 1502 |
| LMArena German | — | 1489 |
| LMArena Japanese | — | 1466 |
| LMArena Korean | — | 1467 |
| LMArena Spanish | — | 1495 |

## Instruction Following

- Qwen2.5-Coder-32B: 61.6 (#240)
- Qwen3.8 Max: 77.7 (#19)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1223 | 1478 |
| LiveBench Instruction Following | 58.7% | — |

## Long Context

- Qwen2.5-Coder-32B: 37.9 (#204)
- Qwen3.8 Max: 45.5 (#30)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1251 | 1486 |

## Writing & Preference

- Qwen2.5-Coder-32B: 41.8 (#235)
- Qwen3.8 Max: 67.0 (#31)

| Benchmark | Qwen2.5-Coder-32B | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1230 | 1480 |
| LMArena Creative Writing | 1174 | 1478 |
| LMArena Multi-Turn | 1222 | 1487 |
| LiveBench Language | 23.3% | — |

## FAQ

### Is Qwen2.5-Coder-32B better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.0 to 32.9 on the Noometry Index. Qwen2.5-Coder-32B costs 4.0× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.

### Which is cheaper, Qwen2.5-Coder-32B or Qwen3.8 Max?

Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Qwen3.8 Max lists at $2 and $6.

### Is Qwen2.5-Coder-32B or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 22.4 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.8 Max does, with 1M tokens against 33K.

### How many benchmarks do Qwen2.5-Coder-32B and Qwen3.8 Max share?

13 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Qwen3.8 Max has 38.