Key Takeaways
Gemini 3 Pro Preview wins:
- Larger context window
- Higher intelligence benchmark
- Better at coding
- Has reasoning mode
GPT-5 Codex wins:
- Cheaper input tokens
- Cheaper output tokens
- Faster response time
- Better at math
Price Advantage
GPT-5 Codex
Benchmark Advantage
Gemini 3 Pro Preview
Context Window
Gemini 3 Pro Preview
Speed
GPT-5 Codex
Pricing Comparison
Price Comparison
| Metric | Gemini 3 Pro Preview | GPT-5 Codex | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $2.00 | $1.25 | GPT-5 Codex |
| Output (per 1M tokens) | $12.00 | $10.00 | GPT-5 Codex |
| Cache Read (per 1M) | $200000.00 | $125000.00 | GPT-5 Codex |
| Cache Write (per 1M) | $375000.00 | N/A | Gemini 3 Pro Preview |
Using a 3:1 input/output ratio, GPT-5 Codex is 24% cheaper overall.
Gemini 3 Pro Preview Providers
Google AI Studio $2.00 (Cheapest)
Google $2.00 (Cheapest)
GPT-5 Codex Providers
OpenAI $1.25 (Cheapest)
Benchmark Comparison
6
Benchmarks Compared
5
Gemini 3 Pro Preview Wins
1
GPT-5 Codex Wins
Benchmark Scores
| Benchmark | Gemini 3 Pro Preview | GPT-5 Codex | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 48.4 | 44.5 | |
Coding Index Code generation & understanding | 46.5 | 38.9 | |
Math Index Mathematical reasoning | 95.7 | 98.7 | |
MMLU Pro Academic knowledge | 89.8 | 86.5 | |
GPQA Graduate-level science | 90.8 | 83.7 | |
LiveCodeBench Competitive programming | 91.7 | 84.0 |
Gemini 3 Pro Preview significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Gemini 3 Pro Preview
Other models
Context & Performance
Context Window
Gemini 3 Pro Preview
1,048,576
tokens
Max output: 65,536 tokens
GPT-5 Codex
400,000
tokens
Max output: 128,000 tokens
Gemini 3 Pro Preview has a 62% larger context window.
Speed Performance
| Metric | Gemini 3 Pro Preview | GPT-5 Codex | Winner |
|---|---|---|---|
| Tokens/second | 130.0 tok/s | 338.6 tok/s | |
| Time to First Token | 29.59s | 14.88s |
GPT-5 Codex responds 161% faster on average.
Capabilities
Feature Comparison
| Feature | Gemini 3 Pro Preview | GPT-5 Codex |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Gemini 3 Pro Preview | GPT-5 Codex |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | OpenAI | |
| Released | Nov 2025 | Sep 2025 |
Gemini 3 Pro Preview Modalities
Input
textimagefileaudiovideo
Output
text
GPT-5 Codex Modalities
Input
textimage
Output
text