# GPT-5.2 Codex vs Qwen2.5 Plus 1127

> GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 38.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-qwen2-5-plus
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5.2 Codex leads 45.4 to 37.9.

## Snapshot

| | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.2 | 38.1 |
| Rank | 107 | 179 |
| Context | 400K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.2 Codex: 45.4 (#66)
- Qwen2.5 Plus 1127: 37.9 (#171)

| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1314 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 40.7 (#20)
- Qwen2.5 Plus 1127: —

| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| Terminal-Bench | 66.5% | — |

## Reasoning

- GPT-5.2 Codex: —
- Qwen2.5 Plus 1127: 24.8 (#139)

| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | — | 1299 |

## Math

- GPT-5.2 Codex: —
- Qwen2.5 Plus 1127: 33.5 (#175)

| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | — | 1298 |

## Knowledge

- GPT-5.2 Codex: —
- Qwen2.5 Plus 1127: 34.9 (#179)

| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | — | 1289 |

## Multilingual

- GPT-5.2 Codex: —
- Qwen2.5 Plus 1127: 42.1 (#196)

| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | — | 1265 |
| LMArena Chinese | — | 1314 |
| LMArena German | — | 1231 |
| LMArena Japanese | — | 1207 |
| LMArena Russian | — | 1271 |

## Instruction Following

- GPT-5.2 Codex: —
- Qwen2.5 Plus 1127: 67.4 (#194)

| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | — | 1275 |

## Long Context

- GPT-5.2 Codex: —
- Qwen2.5 Plus 1127: 39.2 (#180)

| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | — | 1292 |

## Writing & Preference

- GPT-5.2 Codex: —
- Qwen2.5 Plus 1127: 49.5 (#186)

| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | — | 1299 |
| LMArena Creative Writing | — | 1262 |
| LMArena Multi-Turn | — | 1299 |

## FAQ

### Is GPT-5.2 Codex better than Qwen2.5 Plus 1127?

GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 38.1 on the Noometry Index.

### Is GPT-5.2 Codex or Qwen2.5 Plus 1127 better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 37.9 in the Noometry coding category.

### How many benchmarks do GPT-5.2 Codex and Qwen2.5 Plus 1127 share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Qwen2.5 Plus 1127 has 14.