All Comparisons

DeepSeek-V3 vs o3
DeepSeek-V3
DeepSeek π¨π³
22.5
#309β
low$0.32/M in Β· $0.89/M out
163.8K context
o3
OpenAI πΊπΈ
47.4
#202β
highMost Affordable
DeepSeek-V3
$0.32/M input
Largest Context
DeepSeek-V3
163.8K tokens
Best Benchmark Score
o3
47.4/100
Model Specifications
| Spec | DeepSeek-V3 | o3 |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Release Date | Dec 2024 | Apr 2025 |
| Knowledge Cutoff | β | 2024-05-31 |
| Parameters | 671000000000B | Undisclosed |
| Context Window | 163.8K | β |
| Max Output | β | β |
| Open Source | Yes | No |
| License | mit_+_model_license_(commercial_use_allowed) | proprietary |
| Tokenizer | β | β |
| Modality | β | β |
| Reasoning Model | No | No |
| Moderated | No | No |
Pricing Comparison
| Price (per 1M tokens) | DeepSeek-V3 | o3 |
|---|---|---|
| Input | $0.32 | β |
| Output | $0.89 | β |
API Provider Pricing
Capabilities
| Feature | DeepSeek-V3 | o3 |
|---|---|---|
| Text Input | ||
| Image Input (Vision) | ||
| Audio Input | ||
| Video Input | ||
| File Input | ||
| Image Output | ||
| Audio Output | ||
| Tool Use | ||
| Structured Output (JSON) | ||
| Streaming | ||
| Reasoning Tokens | ||
| Web Search | ||
| Temperature Control | ||
| Top-P Sampling | ||
| Stop Sequences | ||
| Seed (Reproducibility) | ||
| Log Probabilities |
Category Comparison
Benchmark-by-Benchmark
general
| Benchmark | DeepSeek-V3 | o3 |
|---|---|---|
| SimpleQA | 24.9 | β |
coding
| Benchmark | DeepSeek-V3 | o3 |
|---|---|---|
| SWE-bench Verified | 42 | 69.1 |
reasoning
| Benchmark | DeepSeek-V3 | o3 |
|---|---|---|
| GPQA Diamond | 59.1 | 83.3 |
| Humanity's Last Exam | β | 14.7 |
| ARC-AGI v2 | β | 6.5 |
math
| Benchmark | DeepSeek-V3 | o3 |
|---|---|---|
| AIME 2025 | β | 86.4 |
| FrontierMath | β | 15.8 |
multimodal
| Benchmark | DeepSeek-V3 | o3 |
|---|---|---|
| MMMU | β | 82.9 |
| MMMU-Pro | β | 76.4 |
| CharXiv Reasoning | β | 78.6 |
agent
| Benchmark | DeepSeek-V3 | o3 |
|---|---|---|
| BrowseComp | β | 49.7 |
Category Winners
coding
58.0
math
43.6
reasoning
34.2
general
30.5
multimodal
72.1
agent
19.6