# GPT-5.4 mini vs Qwen1.5-32B

> GPT-5.4 mini is the stronger model overall, scoring 45.0 to 30.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-qwen1-5-32b
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 86.9% for GPT-5.4 mini and 30.7% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 45.0 | 30.5 |
| Rank | 76 | 293 |
| Context | 400K | — |
| Input $/M | $0.75 | — |
| Output $/M | $4.50 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 mini: 45.2 (#72)
- Qwen1.5-32B: 31.7 (#282)

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1438 | 1155 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.9 (#81)
- Qwen1.5-32B: —

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.4 (#85)
- Qwen1.5-32B: 21.8 (#212)

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1130 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.5 (#75)
- Qwen1.5-32B: 33.0 (#207)

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1419 | 1155 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.5 (#67)
- Qwen1.5-32B: 13.5 (#296)

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 86.9% | 30.7% |
| LMArena Expert | 1435 | 1126 |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
| MMLU | — | 74.4% |

## Multimodal

- GPT-5.4 mini: 39.7 (#56)
- Qwen1.5-32B: —

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 51.9 (#96)
- Qwen1.5-32B: 31.4 (#259)

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1405 | 1106 |
| LMArena Chinese | 1446 | 1177 |
| LMArena French | 1440 | 1101 |
| LMArena German | 1409 | 1058 |
| LMArena Japanese | 1374 | 1027 |
| LMArena Korean | 1368 | 1008 |
| LMArena Russian | 1417 | 1073 |
| LMArena Spanish | 1405 | 1089 |

## Instruction Following

- GPT-5.4 mini: 74.1 (#102)
- Qwen1.5-32B: 57.7 (#265)

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1116 |

## Long Context

- GPT-5.4 mini: 43.0 (#112)
- Qwen1.5-32B: 34.7 (#246)

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1407 | 1146 |

## Writing & Preference

- GPT-5.4 mini: 64.0 (#58)
- Qwen1.5-32B: 34.2 (#271)

| Benchmark | GPT-5.4 mini | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1412 | 1137 |
| LMArena Creative Writing | 1370 | 1083 |
| LMArena Multi-Turn | 1429 | 1140 |
| EQ-Bench Creative Writing | 1665 | — |

## FAQ

### Is GPT-5.4 mini better than Qwen1.5-32B?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 30.5 on the Noometry Index.

### Is GPT-5.4 mini or Qwen1.5-32B better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 31.7 in the Noometry coding category.

### How many benchmarks do GPT-5.4 mini and Qwen1.5-32B share?

18 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen1.5-32B has 21.