GPT-5.1 vs Qwen3 4B
OpenAI vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •GPT-5.1 has the higher intelligence index (89 vs 56.5)
- •Qwen3 4B is cheaper ($0.10 vs $1.25 per 1M input)
- •GPT-5.1 is faster
| GPT-5.1 | Qwen3 4B | |
|---|---|---|
| Intelligence index | 89 | 56.5 |
| Developer | OpenAI | Alibaba |
| Type | LLM | LLM |
| Access | API only | — |
| Context window | 400,000 tokens | — |
| Input price | $1.25 / 1M | $0.10 / 1M |
| Output price | $10.00 / 1M | $0.40 / 1M |
| Speed | 115 tok/s | 103 tok/s |
| Released | November 12, 2025 | April 28, 2025 |
| Parameters | — | — |
| Input modalities | Text, Image | — |
| Output modalities | Text | — |
Shared benchmarks
GPT-5.1
Qwen3 4B
AIME 2025
94
22.3
GPQA Diamond
88.1
52.2
Humanity’s Last Exam
26.5
5.1
LiveCodeBench
86.8
46.5
MMLU-Pro
87
69.6