# GPT-5-Codex vs Qwen Max

> GPT-5-Codex is the stronger model overall, scoring 37.9 to 34.7 on the Noometry Index.

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

## Summary

- The widest gap is in coding, where GPT-5-Codex leads 42.4 to 30.7.
- Qwen Max is cheaper at $1.60 / $6.40 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 33K.

## Snapshot

| | GPT-5-Codex | Qwen Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 37.9 | 34.7 |
| Rank | 192 | 230 |
| Context | 400K | 33K |
| Input $/M | $1.25 | $1.60 |
| Output $/M | $10 | $6.40 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5-Codex: 42.4 (#103)
- Qwen Max: 30.7 (#292)

| Benchmark | GPT-5-Codex | Qwen Max |
|---|---|---|
| Aider Polyglot | — | 21.8% |
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1288 |

## Agentic & Tool Use

- GPT-5-Codex: 31.0 (#72)
- Qwen Max: —

| Benchmark | GPT-5-Codex | Qwen Max |
|---|---|---|
| Terminal-Bench | 44.3% | — |

## Reasoning

- GPT-5-Codex: 30.9 (#83)
- Qwen Max: 25.1 (#151)

| Benchmark | GPT-5-Codex | Qwen Max |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| LMArena Hard Prompts | — | 1269 |

## Math

- GPT-5-Codex: —
- Qwen Max: 22.3 (#276)

| Benchmark | GPT-5-Codex | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| LMArena Math | — | 1275 |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- GPT-5-Codex: —
- Qwen Max: 30.3 (#228)

| Benchmark | GPT-5-Codex | Qwen Max |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| LMArena Expert | — | 1248 |

## Multilingual

- GPT-5-Codex: —
- Qwen Max: 41.8 (#202)

| Benchmark | GPT-5-Codex | Qwen Max |
|---|---|---|
| LMArena Non-English | — | 1263 |
| LMArena Chinese | — | 1254 |
| LMArena French | — | 1330 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1142 |
| LMArena Russian | — | 1274 |
| LMArena Spanish | — | 1290 |

## Instruction Following

- GPT-5-Codex: —
- Qwen Max: 66.5 (#208)

| Benchmark | GPT-5-Codex | Qwen Max |
|---|---|---|
| LMArena Instruction Following | — | 1262 |

## Long Context

- GPT-5-Codex: —
- Qwen Max: 39.4 (#180)

| Benchmark | GPT-5-Codex | Qwen Max |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| LMArena Longer Query | — | 1288 |

## Writing & Preference

- GPT-5-Codex: —
- Qwen Max: 47.8 (#205)

| Benchmark | GPT-5-Codex | Qwen Max |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1248 |
| LMArena Multi-Turn | — | 1277 |

## FAQ

### Is GPT-5-Codex better than Qwen Max?

GPT-5-Codex is the stronger model overall, scoring 37.9 to 34.7 on the Noometry Index.

### Which is cheaper, GPT-5-Codex or Qwen Max?

Qwen Max is cheaper. It lists at $1.60 per million input tokens and $6.40 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

### Is GPT-5-Codex or Qwen Max better for coding?

GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 30.7 in the Noometry coding category.

### Which has the bigger context window?

GPT-5-Codex does, with 400K tokens against 33K.

### How many benchmarks do GPT-5-Codex and Qwen Max share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Qwen Max has 23.