Key Takeaways
DeepSeek V3 0324 wins:
- Cheaper input tokens
- Cheaper output tokens
GPT-5.1-Codex-Mini wins:
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
- Supports vision
Price Advantage
DeepSeek V3 0324
Benchmark Advantage
GPT-5.1-Codex-Mini
Context Window
GPT-5.1-Codex-Mini
Speed
GPT-5.1-Codex-Mini
Pricing Comparison
Price Comparison
| Metric | DeepSeek V3 0324 | GPT-5.1-Codex-Mini | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.20 | $0.25 | DeepSeek V3 0324 |
| Output (per 1M tokens) | $0.77 | $2.00 | DeepSeek V3 0324 |
| Cache Read (per 1M) | $0.14 | $0.03 | GPT-5.1-Codex-Mini |
Using a 3:1 input/output ratio, DeepSeek V3 0324 is 50% cheaper overall.
DeepSeek V3 0324 Providers
DeepInfra $0.20 (Cheapest)
AtlasCloud $0.22
SiliconFlow $0.25
Chutes $0.25
Novita $0.27
GPT-5.1-Codex-Mini Providers
OpenAI $0.25 (Cheapest)
Azure $0.25 (Cheapest)
Benchmark Comparison
8
Benchmarks Compared
0
DeepSeek V3 0324 Wins
6
GPT-5.1-Codex-Mini Wins
Benchmark Scores
| Benchmark | DeepSeek V3 0324 | GPT-5.1-Codex-Mini | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 16.5 | 38.6 | |
Coding Index Code generation & understanding | 16.4 | 36.4 | |
Math Index Mathematical reasoning | 26.0 | 91.7 | |
MMLU Pro Academic knowledge | 75.2 | 82.0 | |
GPQA Graduate-level science | 55.7 | 81.3 | |
LiveCodeBench Competitive programming | 35.9 | 83.6 | |
Aider Real-world code editing | 55.1 | - | - |
AIME Competition math | 25.3 | - | - |
GPT-5.1-Codex-Mini significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
DeepSeek V3 0324
Other models
Context & Performance
Context Window
DeepSeek V3 0324
163,840
tokens
GPT-5.1-Codex-Mini
400,000
tokens
Max output: 100,000 tokens
GPT-5.1-Codex-Mini has a 59% larger context window.
Speed Performance
| Metric | DeepSeek V3 0324 | GPT-5.1-Codex-Mini | Winner |
|---|---|---|---|
| Tokens/second | 0.0 tok/s | 156.7 tok/s | |
| Time to First Token | 0.00s | 7.86s |
GPT-5.1-Codex-Mini responds Infinity% faster on average.
Capabilities
Feature Comparison
| Feature | DeepSeek V3 0324 | GPT-5.1-Codex-Mini |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | DeepSeek V3 0324 | GPT-5.1-Codex-Mini |
|---|---|---|
| License | Open Source | Proprietary |
| Author | Deepseek | OpenAI |
| Released | Mar 2025 | Nov 2025 |
DeepSeek V3 0324 Modalities
Input
text
Output
text
GPT-5.1-Codex-Mini Modalities
Input
imagetext
Output
text