Key Takeaways
Gemini 2.5 Pro Preview 05-06 wins:
- Larger context window
- Has reasoning mode
GPT-5 Codex wins:
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
Price Advantage
Gemini 2.5 Pro Preview 05-06
Benchmark Advantage
GPT-5 Codex
Context Window
Gemini 2.5 Pro Preview 05-06
Speed
GPT-5 Codex
Pricing Comparison
Price Comparison
| Metric | Gemini 2.5 Pro Preview 05-06 | GPT-5 Codex | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $1.25 | $1.25 | Tie |
| Output (per 1M tokens) | $10.00 | $10.00 | Tie |
| Cache Read (per 1M) | $125000.00 | $125000.00 | Tie |
| Cache Write (per 1M) | $375000.00 | N/A | Gemini 2.5 Pro Preview 05-06 |
Both models have similar overall pricing.
Gemini 2.5 Pro Preview 05-06 Providers
Google AI Studio $1.25 (Cheapest)
Google $1.25 (Cheapest)
GPT-5 Codex Providers
OpenAI $1.25 (Cheapest)
Benchmark Comparison
8
Benchmarks Compared
0
Gemini 2.5 Pro Preview 05-06 Wins
4
GPT-5 Codex Wins
Benchmark Scores
| Benchmark | Gemini 2.5 Pro Preview 05-06 | GPT-5 Codex | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 29.5 | 44.5 | |
Coding Index Code generation & understanding | - | 38.9 | - |
Math Index Mathematical reasoning | - | 98.7 | - |
MMLU Pro Academic knowledge | 83.7 | 86.5 | |
GPQA Graduate-level science | 82.2 | 83.7 | |
LiveCodeBench Competitive programming | 77.0 | 84.0 | |
Aider Real-world code editing | 76.9 | - | - |
AIME Competition math | 84.3 | - | - |
GPT-5 Codex significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Gemini 2.5 Pro Preview 05-06
Other models
Context & Performance
Context Window
Gemini 2.5 Pro Preview 05-06
1,048,576
tokens
Max output: 65,535 tokens
GPT-5 Codex
400,000
tokens
Max output: 128,000 tokens
Gemini 2.5 Pro Preview 05-06 has a 62% larger context window.
Speed Performance
| Metric | Gemini 2.5 Pro Preview 05-06 | GPT-5 Codex | Winner |
|---|---|---|---|
| Tokens/second | 0.0 tok/s | 314.7 tok/s | |
| Time to First Token | 0.00s | 10.95s |
GPT-5 Codex responds Infinity% faster on average.
Capabilities
Feature Comparison
| Feature | Gemini 2.5 Pro Preview 05-06 | 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 2.5 Pro Preview 05-06 | GPT-5 Codex |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | OpenAI | |
| Released | May 2025 | Sep 2025 |
Gemini 2.5 Pro Preview 05-06 Modalities
Input
textimagefileaudiovideo
Output
text
GPT-5 Codex Modalities
Input
textimage
Output
text