Gemma 4 31B vs GPT-5.3-Codex
Google vs OpenAI — benchmarks, pricing, and capabilities side by side.
- •GPT-5.3-Codex has the higher intelligence index (91.5 vs 85.7)
- •Gemma 4 31B is cheaper ($0.12 vs $1.75 per 1M input)
- •GPT-5.3-Codex is faster
- •GPT-5.3-Codex has a larger context window (400K)
| Gemma 4 31B | GPT-5.3-Codex | |
|---|---|---|
| Intelligence index | 85.7 | 91.5 |
| Developer | OpenAI | |
| Type | Multimodal | Multimodal |
| Access | Open weights | API only |
| Context window | 262,144 tokens | 400,000 tokens |
| Input price | $0.12 / 1M | $1.75 / 1M |
| Output price | $0.37 / 1M | $14.00 / 1M |
| Speed | 36 tok/s | 73 tok/s |
| Released | April 2, 2026 | February 24, 2026 |
| Parameters | — | — |
| Input modalities | Image, Text, Video | Text, Image |
| Output modalities | Text | Text |
Shared benchmarks
Gemma 4 31B
GPT-5.3-Codex
GPQA Diamond
85.7
91.5
Humanity’s Last Exam
22.7
39.9