DeepSeek V3.2 vs GPT-4o-mini
Head to head on 15 shared benchmarks, with price, context window, and release dates.
Benchmark scores
54evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 DeepSeek | 74.2% | 59.0% | 47.9% | 1511elo | 75.1% | 11.2% | 49.0% | 65.9% | 64.6% | 48.2% | 70.4% | 59.3% | 83.7% | 38.7% | 68.2% | 74.7% | - | - | - | - | - | 0.0% | 16.0% | - | 66.8 | 22.1% | - | - | - | 31.3% | 68.0% | - | 50.0% | 85.0% | 77.2% | - | 57.5% | - | - | - | 8.0% | - | 59.0% | 70.0% | - | 32.6% | 65 | - | 5.1% | - | - | - | - | 78.9% | 51.7% |
| GPT-4o-mini OpenAI | 3.6% | 14.7% | 45.5% | 871elo | 42.6% | 4.2% | 31.0% | 47.2% | 43.0% | 65.8% | 32.9% | 23.4% | 64.8% | 22.9% | 60.5% | - | 16.7% | 11.7% | 50.7% | 0.29 | 0.0% | - | - | 0.0% | - | - | 0.0% | 1.54 | 0.0% | - | - | 72.0% | - | - | - | 78.9% | - | 62.8% | 54.5% | 78.0% | - | 3.81 | - | - | 100.0% | - | - | 0.36 | - | 0.78 | 83.3% | 54.5% | 22.5% | - | 39.6% |
2 / 2 models
| Attribute | DeepSeek V3.2 DeepSeek | GPT-4o-mini OpenAI |
|---|---|---|
| Description | DeepSeek V3.2 is an AI model from DeepSeek, released with open weights. | GPT-4o Mini is an AI model from OpenAI. |
| Family | Deepseek | GPT |
| Params | - | - |
| Open weights | open | closed |
| License | mit | proprietary |
| Released | 1 Dec 2025 | 18 Jul 2024 |
| Context | 163,840 | 128,000 |
| Input $/1M | $0.28 | $0.15 |
| Output $/1M | $0.42 | $0.60 |
| Cache read $/1M | $0.130 | $0.075 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text | text, image, file |
| Providers | - | - |
| Publisher | DeepSeek | OpenAI |
| Reported scores | Aider Polyglot Benchmark74.2% (Aider) MathArena57.47% GPQA Diamond75.1% (AA) Humanity's Last Exam (HLE)11.2% (AA) |
FAQ
- Is DeepSeek V3.2 or GPT-4o-mini better?
- Across the 15 benchmarks both models report on Sophon, DeepSeek V3.2 leads on 14 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do DeepSeek V3.2 and GPT-4o-mini compare on GPQA Diamond?
- DeepSeek V3.2 scores 75.1% and GPT-4o-mini scores 42.6% on GPQA Diamond.
- Which is cheaper, DeepSeek V3.2 or GPT-4o-mini?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $0.60 for GPT-4o-mini - about 1.4x.
- When were DeepSeek V3.2 and GPT-4o-mini released?
- DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek. GPT-4o-mini was released 18 Jul 2024 by OpenAI.
Comparing something else? Build your own side-by-side.