Key Takeaways
GPT-5.3 Codex wins:
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Has reasoning mode
Step3 wins:
- Cheaper input tokens
- Cheaper output tokens
Price Advantage
Step3
Benchmark Advantage
GPT-5.3 Codex
Context Window
GPT-5.3 Codex
Speed
GPT-5.3 Codex
Pricing Comparison
Price Comparison
| Metric | GPT-5.3 Codex | Step3 | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $1.75 | $0.57 | Step3 |
| Output (per 1M tokens) | $14.00 | $1.42 | Step3 |
| Cache Read (per 1M) | $0.17 | N/A | GPT-5.3 Codex |
Using a 3:1 input/output ratio, Step3 is 84% cheaper overall.
GPT-5.3 Codex Providers
No provider data available
Step3 Providers
No provider data available
Benchmark Comparison
3
Benchmarks Compared
0
GPT-5.3 Codex Wins
0
Step3 Wins
Benchmark Scores
| Benchmark | GPT-5.3 Codex | Step3 | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 54.0 | - | - |
Coding Index Code generation & understanding | 53.1 | - | - |
GPQA Graduate-level science | 91.5 | - | - |
GPT-5.3 Codex significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Other models
Context & Performance
Context Window
GPT-5.3 Codex
400,000
tokens
Step3
256,000
tokens
GPT-5.3 Codex has a 36% larger context window.
Speed Performance
| Metric | GPT-5.3 Codex | Step3 | Winner |
|---|---|---|---|
| Tokens/second | 63.8 tok/s | N/A | |
| Time to First Token | 83.49s | N/A |
Capabilities
Feature Comparison
| Feature | GPT-5.3 Codex | Step3 |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | GPT-5.3 Codex | Step3 |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | OpenAI | Stepfun-ai |
| Released | Feb 2026 | Unknown |
GPT-5.3 Codex Modalities
Input
textimage
Output
text
Step3 Modalities
Input
Output