# GPT-5.4 mini vs Qwen3-Coder 480B-A35B Instruct

> GPT-5.4 mini is the stronger model overall, scoring 44.8 to 37.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-qwen3-coder-480b-a35b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GPT-5.4 mini scores higher in 9 categories and Qwen3-Coder 480B-A35B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.4 to 36.4.
- The biggest single-benchmark swing is WeirdML: 60.3% for GPT-5.4 mini and 41.2% for Qwen3-Coder 480B-A35B Instruct.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- GPT-5.4 mini accepts more context: 400K tokens versus 262K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 44.8 | 37.7 |
| Rank | 69 | 186 |
| Context | 400K | 262K |
| Input $/M | $0.75 | $1.50 |
| Output $/M | $4.50 | $7.50 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 mini: 45.0 (#67)
- Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena WebDev | 1397 | 1275 |
| WeirdML | 60.3% | 41.2% |
| LMArena Coding | 1438 | 1413 |
| ALE-Bench | 1,189 | 461.45 |
| FrontierCode | 27% | — |
| SWE-bench Verified (bash only) | — | 55.4% |
| SciCode | 49.9% | — |
| GSO | — | 4.9% |
| AlgoTune | — | 1.44 |

## Agentic & Tool Use

- GPT-5.4 mini: 29.6 (#74)
- Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.3 (#77)
- Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 37.9% | 49.5% |
| LMArena Hard Prompts | 1424 | 1372 |
| ARC-AGI-2 | 18.9% | — |
| 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 | 148.83 | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.4 (#63)
- Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1418 | 1364 |
| 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: 51.4 (#62)
- Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1434 | 1337 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |

## Multimodal

- GPT-5.4 mini: 39.0 (#51)
- Qwen3-Coder 480B-A35B Instruct: —

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 52.1 (#94)
- Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1405 | 1345 |
| LMArena Chinese | 1446 | 1356 |
| LMArena French | 1440 | 1394 |
| LMArena German | 1407 | 1324 |
| LMArena Japanese | 1375 | 1309 |
| LMArena Korean | 1369 | 1307 |
| LMArena Russian | 1417 | 1367 |
| LMArena Spanish | 1403 | 1360 |

## Instruction Following

- GPT-5.4 mini: 74.3 (#99)
- Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1405 | 1356 |

## Long Context

- GPT-5.4 mini: 42.9 (#107)
- Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1407 | 1379 |

## Writing & Preference

- GPT-5.4 mini: 64.2 (#56)
- Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)

| Benchmark | GPT-5.4 mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1411 | 1356 |
| LMArena Creative Writing | 1370 | 1333 |
| LMArena Multi-Turn | 1429 | 1365 |
| EQ-Bench Creative Writing | 1665 | — |

## FAQ

### Is GPT-5.4 mini better than Qwen3-Coder 480B-A35B Instruct?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 37.7 on the Noometry Index.

### Which is cheaper, GPT-5.4 mini or Qwen3-Coder 480B-A35B Instruct?

GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.

### Is GPT-5.4 mini or Qwen3-Coder 480B-A35B Instruct better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 36.2 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 262K.

### How many benchmarks do GPT-5.4 mini and Qwen3-Coder 480B-A35B Instruct share?

21 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.