Key Takeaways
GPT-5.2-Codex wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Supports vision
text-davinci-003 wins:
- No clear advantages in compared metrics
Price Advantage
GPT-5.2-Codex
Benchmark Advantage
GPT-5.2-Codex
Context Window
GPT-5.2-Codex
Speed
GPT-5.2-Codex
Pricing Comparison
Price Comparison
| Metric | GPT-5.2-Codex | text-davinci-003 | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $1.75 | $20.00 | GPT-5.2-Codex |
| Output (per 1M tokens) | $14.00 | $20.00 | GPT-5.2-Codex |
| Cache Read (per 1M) | $0.17 | N/A | GPT-5.2-Codex |
Using a 3:1 input/output ratio, GPT-5.2-Codex is 76% cheaper overall.
GPT-5.2-Codex Providers
No provider data available
text-davinci-003 Providers
No provider data available
Benchmark Comparison
3
Benchmarks Compared
0
GPT-5.2-Codex Wins
0
text-davinci-003 Wins
Benchmark Scores
| Benchmark | GPT-5.2-Codex | text-davinci-003 | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 49.0 | - | - |
Coding Index Code generation & understanding | 43.0 | - | - |
GPQA Graduate-level science | 89.9 | - | - |
GPT-5.2-Codex significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Other models
Context & Performance
Context Window
GPT-5.2-Codex
400,000
tokens
text-davinci-003
N/A
tokens
Speed Performance
| Metric | GPT-5.2-Codex | text-davinci-003 | Winner |
|---|---|---|---|
| Tokens/second | 72.4 tok/s | N/A | |
| Time to First Token | 7.11s | N/A |
Capabilities
Feature Comparison
| Feature | GPT-5.2-Codex | text-davinci-003 |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | GPT-5.2-Codex | text-davinci-003 |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | OpenAI | OpenAI |
| Released | Jan 2026 | Unknown |
GPT-5.2-Codex Modalities
Input
textimage
Output
text
text-davinci-003 Modalities
Input
Output