# GPT-5.4 mini vs Qwen-14B

> GPT-5.4 mini is the stronger model overall, scoring 44.8 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-qwen-14b
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. GPT-5.4 mini scores higher in 7 categories and Qwen-14B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.4 mini leads 64.2 to 27.8.
- Qwen-14B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 44.8 | 30.8 |
| Rank | 69 | 273 |
| Context | 400K | — |
| Input $/M | $0.75 | — |
| Output $/M | $4.50 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 mini: 45.0 (#67)
- Qwen-14B: 30.6 (#283)

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| LMArena Coding | 1438 | 1072 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.6 (#74)
- Qwen-14B: —

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.3 (#77)
- Qwen-14B: 18.7 (#255)

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1027 |
| Epoch Capabilities Index | 148.83 | 112.8 |
| 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% | — |
| BIG-Bench Hard | — | 55% |
| ForecastBench | 57 | — |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |

## Math

- GPT-5.4 mini: 45.4 (#63)
- Qwen-14B: 28.7 (#224)

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| LMArena Math | 1418 | 1068 |
| 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% | — |
| GSM8K | — | 61.3% |

## Knowledge

- GPT-5.4 mini: 51.4 (#62)
- Qwen-14B: —

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1434 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |

## Multimodal

- GPT-5.4 mini: 39.0 (#51)
- Qwen-14B: —

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 52.1 (#94)
- Qwen-14B: 27.7 (#270)

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1405 | 1042 |
| LMArena Chinese | 1446 | 1077 |
| LMArena French | 1440 | — |
| LMArena German | 1407 | — |
| LMArena Japanese | 1375 | — |
| LMArena Korean | 1369 | — |
| LMArena Russian | 1417 | — |
| LMArena Spanish | 1403 | — |

## Instruction Following

- GPT-5.4 mini: 74.3 (#99)
- Qwen-14B: 52.6 (#284)

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1031 |

## Long Context

- GPT-5.4 mini: 42.9 (#107)
- Qwen-14B: 31.3 (#276)

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1407 | 1029 |

## Writing & Preference

- GPT-5.4 mini: 64.2 (#56)
- Qwen-14B: 27.8 (#294)

| Benchmark | GPT-5.4 mini | Qwen-14B |
|---|---|---|
| LMArena Text | 1411 | 1051 |
| LMArena Creative Writing | 1370 | 1028 |
| LMArena Multi-Turn | 1429 | 1022 |
| EQ-Bench Creative Writing | 1665 | — |

## FAQ

### Is GPT-5.4 mini better than Qwen-14B?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 30.8 on the Noometry Index.

### Is GPT-5.4 mini or Qwen-14B better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 30.6 in the Noometry coding category.

### How many benchmarks do GPT-5.4 mini and Qwen-14B share?

11 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen-14B has 18.