# GPT-5.2 Codex vs Qwen2-72B

> GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 40.7 to 16.9.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.2 | 29.5 |
| Rank | 107 | 294 |
| Context | 400K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Codex: 45.4 (#66)
- Qwen2-72B: 28.7 (#303)

| Benchmark | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LMArena Coding | — | 1196 |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 40.7 (#20)
- Qwen2-72B: 16.9 (#138)

| Benchmark | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| Terminal-Bench | 66.5% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- GPT-5.2 Codex: —
- Qwen2-72B: 22.2 (#184)

| Benchmark | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | — | 1191 |
| Epoch Capabilities Index | — | 125.27 |

## Math

- GPT-5.2 Codex: —
- Qwen2-72B: 27.9 (#232)

| Benchmark | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- GPT-5.2 Codex: —
- Qwen2-72B: 21.2 (#270)

| Benchmark | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |

## Multilingual

- GPT-5.2 Codex: —
- Qwen2-72B: 36.0 (#239)

| Benchmark | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1169 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1168 |

## Instruction Following

- GPT-5.2 Codex: —
- Qwen2-72B: 62.0 (#236)

| Benchmark | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |

## Long Context

- GPT-5.2 Codex: —
- Qwen2-72B: 36.1 (#230)

| Benchmark | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1193 |

## Writing & Preference

- GPT-5.2 Codex: —
- Qwen2-72B: 41.0 (#236)

| Benchmark | GPT-5.2 Codex | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1195 |

## FAQ

### Is GPT-5.2 Codex better than Qwen2-72B?

GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 29.5 on the Noometry Index.

### Is GPT-5.2 Codex or Qwen2-72B better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 28.7 in the Noometry coding category.

### How many benchmarks do GPT-5.2 Codex and Qwen2-72B share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Qwen2-72B has 26.