# GPT-5.2 Codex vs Qwen3.5 Max Preview

> Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 42.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-qwen3-5-max-preview
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Snapshot

| | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.2 | 44.7 |
| Rank | 107 | 72 |
| Context | 400K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.2 Codex: 45.4 (#66)
- Qwen3.5 Max Preview: 43.4 (#79)

| Benchmark | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1488 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 40.7 (#20)
- Qwen3.5 Max Preview: —

| Benchmark | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| Terminal-Bench | 66.5% | — |

## Reasoning

- GPT-5.2 Codex: —
- Qwen3.5 Max Preview: 29.6 (#81)

| Benchmark | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | — | 1483 |

## Math

- GPT-5.2 Codex: —
- Qwen3.5 Max Preview: 37.3 (#99)

| Benchmark | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | — | 1473 |

## Knowledge

- GPT-5.2 Codex: —
- Qwen3.5 Max Preview: 41.1 (#104)

| Benchmark | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | — | 1489 |

## Multilingual

- GPT-5.2 Codex: —
- Qwen3.5 Max Preview: 56.4 (#21)

| Benchmark | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | — | 1465 |
| LMArena Chinese | — | 1534 |
| LMArena French | — | 1483 |
| LMArena German | — | 1487 |
| LMArena Japanese | — | 1497 |
| LMArena Korean | — | 1438 |
| LMArena Russian | — | 1472 |
| LMArena Spanish | — | 1470 |

## Instruction Following

- GPT-5.2 Codex: —
- Qwen3.5 Max Preview: 77.2 (#28)

| Benchmark | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | — | 1467 |

## Long Context

- GPT-5.2 Codex: —
- Qwen3.5 Max Preview: 45.2 (#44)

| Benchmark | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | — | 1477 |

## Writing & Preference

- GPT-5.2 Codex: —
- Qwen3.5 Max Preview: 66.1 (#39)

| Benchmark | GPT-5.2 Codex | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | — | 1471 |
| LMArena Creative Writing | — | 1464 |
| LMArena Multi-Turn | — | 1478 |

## FAQ

### Is GPT-5.2 Codex better than Qwen3.5 Max Preview?

Qwen3.5 Max Preview is the stronger model overall, scoring 44.7 to 42.2 on the Noometry Index.

### Is GPT-5.2 Codex or Qwen3.5 Max Preview better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 43.4 in the Noometry coding category.

### How many benchmarks do GPT-5.2 Codex and Qwen3.5 Max Preview share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Qwen3.5 Max Preview has 17.