# GPT-4 vs Qwen Plus

> Qwen Plus is the stronger model overall, scoring 36.7 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-vs-qwen-plus
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Plus leads 52.4 to 35.0.
- The biggest single-benchmark swing is MATH Level 5: 23% for GPT-4 and 65.3% for Qwen Plus.
- Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $30 / $60 for GPT-4.
- Qwen Plus accepts more context: 1M tokens versus 8K.

## Snapshot

| | GPT-4 | Qwen Plus |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 28.9 | 36.7 |
| Rank | 308 | 204 |
| Context | 8K | 1M |
| Input $/M | $30 | $0.40 |
| Output $/M | $60 | $1.20 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4: 31.2 (#277)
- Qwen Plus: 38.3 (#163)

| Benchmark | GPT-4 | Qwen Plus |
|---|---|---|
| LMArena Coding | 1254 | 1328 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- Qwen Plus: —

| Benchmark | GPT-4 | Qwen Plus |
|---|---|---|
| METR Time Horizons | 36.1% | — |

## Reasoning

- GPT-4: 17.3 (#285)
- Qwen Plus: 27.6 (#101)

| Benchmark | GPT-4 | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1317 |
| DTBench | 62.7% | 81.1% |
| LMCA | 17.1% | 24% |
| Kagi LLM Benchmark | — | 63.3% |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.88 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |

## Math

- GPT-4: 10.1 (#304)
- Qwen Plus: 22.0 (#266)

| Benchmark | GPT-4 | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 17.8% |
| LMArena Math | 1269 | 1326 |
| MATH Level 5 | 23% | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| GSM8K | 92% | — |

## Knowledge

- GPT-4: 18.4 (#277)
- Qwen Plus: 27.4 (#245)

| Benchmark | GPT-4 | Qwen Plus |
|---|---|---|
| GPQA Diamond | 35.7% | 48.1% |
| LMArena Expert | 1211 | 1328 |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |

## Multilingual

- GPT-4: 40.8 (#210)
- Qwen Plus: 45.3 (#170)

| Benchmark | GPT-4 | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1246 | 1310 |
| LMArena Chinese | 1242 | 1347 |
| LMArena Japanese | 1209 | 1251 |
| LMArena Russian | 1251 | 1323 |
| LMArena French | 1282 | — |
| LMArena German | 1251 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1261 | — |

## Instruction Following

- GPT-4: 65.5 (#217)
- Qwen Plus: 69.0 (#176)

| Benchmark | GPT-4 | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1241 | 1303 |

## Long Context

- GPT-4: 37.7 (#207)
- Qwen Plus: 40.3 (#153)

| Benchmark | GPT-4 | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1244 | 1325 |

## Writing & Preference

- GPT-4: 35.0 (#263)
- Qwen Plus: 52.4 (#171)

| Benchmark | GPT-4 | Qwen Plus |
|---|---|---|
| LMArena Text | 1263 | 1326 |
| LMArena Creative Writing | 1244 | 1293 |
| LMArena Multi-Turn | 1257 | 1336 |
| EQ-Bench Creative Writing | 752 | — |

## FAQ

### Is GPT-4 better than Qwen Plus?

Qwen Plus is the stronger model overall, scoring 36.7 to 28.9 on the Noometry Index.

### Which is cheaper, GPT-4 or Qwen Plus?

Qwen Plus is cheaper. It lists at $0.40 per million input tokens and $1.20 per million output tokens; GPT-4 lists at $30 and $60.

### Is GPT-4 or Qwen Plus better for coding?

Qwen Plus scores higher on coding benchmarks: 38.3 versus 31.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen Plus does, with 1M tokens against 8K.

### How many benchmarks do GPT-4 and Qwen Plus share?

18 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen Plus has 20.