# GPT-4 vs Qwen-7B

> GPT-4 has enough public results to be ranked (#308); Qwen-7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/gpt-4-vs-qwen-7b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both.
- Qwen-7B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4 | Qwen-7B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 28.9 | — |
| Rank | 308 | — |
| Context | 8K | — |
| Input $/M | $30 | — |
| Output $/M | $60 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-4: 31.2 (#277)
- Qwen-7B: —

| Benchmark | GPT-4 | Qwen-7B |
|---|---|---|
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| LMArena Coding | 1254 | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- Qwen-7B: —

| Benchmark | GPT-4 | Qwen-7B |
|---|---|---|
| METR Time Horizons | 36.1% | — |

## Reasoning

- GPT-4: 17.3 (#285)
- Qwen-7B: —

| Benchmark | GPT-4 | Qwen-7B |
|---|---|---|
| BIG-Bench Hard | 75.1% | 45% |
| Epoch Capabilities Index | 125.88 | 106.47 |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | 1241 | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| LAMBADA | — | 67.9% |
| PIQA | — | 77.9% |
| WinoGrande | 87.5% | — |

## Math

- GPT-4: 10.1 (#304)
- Qwen-7B: —

| Benchmark | GPT-4 | Qwen-7B |
|---|---|---|
| GSM8K | 92% | 51.7% |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| LMArena Math | 1269 | — |
| MATH Level 5 | 23% | — |

## Knowledge

- GPT-4: 18.4 (#277)
- Qwen-7B: —

| Benchmark | GPT-4 | Qwen-7B |
|---|---|---|
| MMLU | 86.4% | 45% |
| GPQA Diamond | 35.7% | — |
| LMArena Expert | 1211 | — |
| ARC (AI2) Challenge | — | 75.3% |
| BoolQ | — | 76.4% |
| TriviaQA | 84.8% | — |

## Multilingual

- GPT-4: 40.8 (#210)
- Qwen-7B: —

| Benchmark | GPT-4 | Qwen-7B |
|---|---|---|
| LMArena Non-English | 1246 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1282 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1251 | — |
| LMArena Spanish | 1261 | — |

## Instruction Following

- GPT-4: 65.5 (#217)
- Qwen-7B: —

| Benchmark | GPT-4 | Qwen-7B |
|---|---|---|
| LMArena Instruction Following | 1241 | — |

## Long Context

- GPT-4: 37.7 (#207)
- Qwen-7B: —

| Benchmark | GPT-4 | Qwen-7B |
|---|---|---|
| LMArena Longer Query | 1244 | — |

## Writing & Preference

- GPT-4: 35.0 (#263)
- Qwen-7B: —

| Benchmark | GPT-4 | Qwen-7B |
|---|---|---|
| LMArena Text | 1263 | — |
| LMArena Creative Writing | 1244 | — |
| EQ-Bench Creative Writing | 752 | — |
| LMArena Multi-Turn | 1257 | — |

## FAQ

### Is GPT-4 better than Qwen-7B?

GPT-4 has enough public results to be ranked (#308); Qwen-7B does not yet, so treat this comparison as directional.

### How many benchmarks do GPT-4 and Qwen-7B share?

4 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen-7B has 8.