Key Takeaways
GPT-5.3 Codex wins:
- Larger context window
- Higher intelligence benchmark
- Better at coding
- Supports vision
- Has reasoning mode
- Supports tool calls
Nemotron-3 Super 120B A12B wins:
- Cheaper input tokens
- Cheaper output tokens
- Faster response time
Price Advantage
Nemotron-3 Super 120B A12B
Benchmark Advantage
GPT-5.3 Codex
Context Window
GPT-5.3 Codex
Speed
Nemotron-3 Super 120B A12B
Pricing Comparison
Price Comparison
| Metric | GPT-5.3 Codex | Nemotron-3 Super 120B A12B | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $1.75 | $0.10 | Nemotron-3 Super 120B A12B |
| Output (per 1M tokens) | $14.00 | $0.50 | Nemotron-3 Super 120B A12B |
| Cache Read (per 1M) | $0.17 | N/A | GPT-5.3 Codex |
Using a 3:1 input/output ratio, Nemotron-3 Super 120B A12B is 96% cheaper overall.
GPT-5.3 Codex Providers
No provider data available
Nemotron-3 Super 120B A12B Providers
No provider data available
Benchmark Comparison
3
Benchmarks Compared
3
GPT-5.3 Codex Wins
0
Nemotron-3 Super 120B A12B Wins
Benchmark Scores
| Benchmark | GPT-5.3 Codex | Nemotron-3 Super 120B A12B | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 54.0 | 36.0 | |
Coding Index Code generation & understanding | 53.1 | 31.2 | |
GPQA Graduate-level science | 91.5 | 80.0 |
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
Nemotron-3 Super 120B A12B
N/A
tokens
Speed Performance
| Metric | GPT-5.3 Codex | Nemotron-3 Super 120B A12B | Winner |
|---|---|---|---|
| Tokens/second | 74.0 tok/s | 429.8 tok/s | |
| Time to First Token | 85.27s | 0.57s |
Nemotron-3 Super 120B A12B responds 481% faster on average.
Capabilities
Feature Comparison
| Feature | GPT-5.3 Codex | Nemotron-3 Super 120B A12B |
|---|---|---|
| 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 | Nemotron-3 Super 120B A12B |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | OpenAI | Nvidia |
| Released | Feb 2026 | Unknown |
GPT-5.3 Codex Modalities
Input
textimage
Output
text
Nemotron-3 Super 120B A12B Modalities
Input
Output