# GPT-5.3 Codex vs Qwen1.5-32B

> GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 30.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-3-codex-vs-qwen1-5-32b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 31.7.
- Qwen1.5-32B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 45.8 | 30.5 |
| Rank | 69 | 293 |
| Context | 400K | — |
| Input $/M | $1.75 | — |
| Output $/M | $14 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.3 Codex: 48.6 (#56)
- Qwen1.5-32B: 31.7 (#282)

| Benchmark | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| SWE-bench Verified | 74.8% | — |
| LMArena WebDev | 1409 | — |
| WeirdML | 79.3% | — |
| BigCodeBench Instruct | — | 32.3% |
| LMArena Coding | — | 1155 |
| BigCodeBench Complete | — | 42% |
| ALE-Bench | 1,655 | — |

## Agentic & Tool Use

- GPT-5.3 Codex: 48.0 (#9)
- Qwen1.5-32B: —

| Benchmark | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |

## Reasoning

- GPT-5.3 Codex: —
- Qwen1.5-32B: 21.8 (#212)

| Benchmark | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | — | 1130 |
| Epoch Capabilities Index | 156.77 | — |

## Math

- GPT-5.3 Codex: —
- Qwen1.5-32B: 33.0 (#207)

| Benchmark | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| LMArena Math | — | 1155 |

## Knowledge

- GPT-5.3 Codex: —
- Qwen1.5-32B: 13.5 (#296)

| Benchmark | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | — | 30.7% |
| LMArena Expert | — | 1126 |
| MMLU | — | 74.4% |

## Multilingual

- GPT-5.3 Codex: —
- Qwen1.5-32B: 31.4 (#259)

| Benchmark | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | — | 1106 |
| LMArena Chinese | — | 1177 |
| LMArena French | — | 1101 |
| LMArena German | — | 1058 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1008 |
| LMArena Russian | — | 1073 |
| LMArena Spanish | — | 1089 |

## Instruction Following

- GPT-5.3 Codex: —
- Qwen1.5-32B: 57.7 (#265)

| Benchmark | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | — | 1116 |

## Long Context

- GPT-5.3 Codex: —
- Qwen1.5-32B: 34.7 (#246)

| Benchmark | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | — | 1146 |

## Writing & Preference

- GPT-5.3 Codex: —
- Qwen1.5-32B: 34.2 (#271)

| Benchmark | GPT-5.3 Codex | Qwen1.5-32B |
|---|---|---|
| LMArena Text | — | 1137 |
| LMArena Creative Writing | — | 1083 |
| LMArena Multi-Turn | — | 1140 |

## FAQ

### Is GPT-5.3 Codex better than Qwen1.5-32B?

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 30.5 on the Noometry Index.

### Is GPT-5.3 Codex or Qwen1.5-32B better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 31.7 in the Noometry coding category.

### How many benchmarks do GPT-5.3 Codex and Qwen1.5-32B share?

0 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Qwen1.5-32B has 21.