DeepSeek V3.2 vs GPT-5
Head to head on 19 shared benchmarks, with price, context window, and release dates.
Benchmark scores
76evals · sort by any column, ⤢ to expand fullscreen
| Model | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5 OpenAI | 88.0% | 94.3% | 61.1% | 1627elo | 72.8 | 32.4% | 85.4% | 28.5% | 73.1% | 83.4% | 84.6% | 87.1% | 18.0% | 42.9% | 74.4% | 73.4% | 32.6% | 20.1% | 84.8% | 46.7% | - | 91.1% | 94.6% | 0.0% | 0.15 | 0.0% | 68.1% | 4.58 | - | - | 57.7% | 80.0% | 80.0% | 91.7% | 0.0% | 88.9% | 83.3% | 100.0% | 48.9% | - | 58.2% | - | - | - | - | - | - | - | 37.5% | 0.52 | 1.62 | 100.0% | 99.4% | - | 0.0% | 92.7% | 92.7% | 49.6% | 83.7% | 93.3% | 10.0% | 0.0% | 65.5% | 60.0% | 0.26 | 0.0% | 43.7% | 74.9% | - | 2.34 | - | 87.5% | 0.86 | 54.8% | 90.0% | 90.0% | 61.9% |
| DeepSeek V3.2 DeepSeek | 74.2% | 92.0% | 47.9% | 1515elo | 66.8 | 22.1% | 84.0% | 24.6% | 60.7% | 68.0% | 86.2% | 86.2% | 8.0% | 38.9% | 70.0% | 68.2% | 35.6% | 5.1% | 90.6% | - | 74.7% | - | - | - | - | - | - | - | 0.0% | 13.0% | - | - | - | - | - | - | - | - | - | 31.3% | - | 65.9% | 64.6% | 50.0% | 48.2% | 70.4% | 85.0% | 77.2% | - | - | - | - | - | 57.5% | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 59.0% | - | 65 | - | - | - | - | - | 55.3% |
2 / 2 models
| Attribute | DeepSeek V3.2 DeepSeek | GPT-5 OpenAI |
|---|---|---|
| Description | DeepSeek V3.2 is an AI model from DeepSeek, released with open weights. | OpenAI's August 2025 unified frontier model that auto-routes between a fast model and a deeper "thinking" variant. |
| Family | Deepseek | GPT 5 |
| Params | - | Undisclosed (closed) |
| Open weights | open | closed |
| License | mit | proprietary |
| Released | 1 Dec 2025 | 7 Aug 2025 |
| Context | 163,840 | 400,000 |
| Input $/1M | $0.28 | $1.25 |
| Output $/1M | $0.42 | $10.00 |
| Cache read $/1M | $0.140 | $0.125 |
| Cache write $/1M | - | - |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text | text, image, file |
| Providers | - | openai |
| Publisher | DeepSeek | OpenAI |
| Reported scores | Aider Polyglot Benchmark74.2% (Aider) MathArena57.47% GPQA Diamond84.0% (AA) Humanity's Last Exam (HLE)24.6% (AA) | SWE-bench74.9% (Verified) GPQA Diamond85.4% (AA) Humanity's Last Exam (HLE)28.5% (AA) IFBench73.1% (AA) |
FAQ
- Is DeepSeek V3.2 or GPT-5 better?
- Across the 19 benchmarks both models report on Sophon, GPT-5 leads on 16 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do DeepSeek V3.2 and GPT-5 compare on GPQA Diamond?
- DeepSeek V3.2 scores 84.0% and GPT-5 scores 85.4% on GPQA Diamond.
- Which is cheaper, DeepSeek V3.2 or GPT-5?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $10.00 for GPT-5 - about 23.8x.
- When were DeepSeek V3.2 and GPT-5 released?
- DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek. GPT-5 was released 7 Aug 2025 by OpenAI.
Other head-to-heads
56GPT-4.1 Mini vs GPT-541 shared evalsGPT-5 vs GPT-5 Mini36 shared evalsClaude Sonnet 4.5 vs GPT-531 shared evalsDeepSeek V3.2 vs GPT-5.229 shared evalsGPT-5 vs GPT-5 Nano28 shared evalsGPT-4.1 vs GPT-528 shared evalsClaude Sonnet 4.5 vs DeepSeek V3.227 shared evalsClaude Opus 4.5 vs DeepSeek V3.227 shared evalsDeepSeek V3.2 vs GPT-5 Mini26 shared evalsClaude Opus 4.6 vs DeepSeek V3.226 shared evalsDeepSeek V3.2 vs Grok 4.1 Fast26 shared evalsClaude 4 Sonnet vs GPT-525 shared evalsDeepSeek V3.2 vs Kimi K2.525 shared evalsGemini 2.5 Pro vs GPT-524 shared evalsDeepSeek V3.2 vs Gemini 3.1 Pro Preview24 shared evalsDeepSeek V3.2 vs GPT-5.424 shared evalsDeepSeek V3.2 vs GLM 5.124 shared evalsGPT-5 vs GPT-5.223 shared evalsClaude Opus 4.5 vs GPT-523 shared evalsDeepSeek V3.2 vs GPT-5.523 shared evalsClaude Sonnet 4.6 vs DeepSeek V3.223 shared evalsClaude Opus 4.7 vs DeepSeek V3.223 shared evalsDeepSeek V3.2 vs gpt-oss-120b23 shared evalsDeepSeek V3.2 vs GPT-5 Nano22 shared evalsClaude Opus 4.8 vs DeepSeek V3.222 shared evalsDeepSeek V3.2 vs GLM 4.722 shared evalsDeepSeek V3.2 vs GPT-5.4 Mini22 shared evalsGPT-4.1 Nano vs GPT-521 shared evalsClaude 4 Sonnet vs DeepSeek V3.221 shared evalsDeepSeek V3.2 vs Gemini 2.5 Pro21 shared evalsGPT-5 vs Grok 4.1 Fast20 shared evalsClaude Fable 5 vs DeepSeek V3.220 shared evalsDeepSeek V3.2 vs Qwen3.6 Plus20 shared evalsGemini 3.1 Pro Preview vs GPT-519 shared evalsClaude Opus 4.6 vs GPT-519 shared evalsGPT-5 vs GPT-5.419 shared evalsGPT-4o vs GPT-519 shared evalsGPT-5 vs GPT-5.518 shared evalsGPT-5 vs Kimi K2.518 shared evalsDeepSeek V3.2 vs GPT-4o18 shared evalsClaude Opus 4.8 vs GPT-517 shared evalsClaude Opus 4.7 vs GPT-517 shared evalsGPT-5 vs gpt-oss-120b17 shared evalsGLM 4.7 vs GPT-517 shared evalsClaude Fable 5 vs GPT-516 shared evalsGPT-4o-mini vs GPT-516 shared evalsClaude Sonnet 4.6 vs GPT-516 shared evalsGLM 5.1 vs GPT-516 shared evalsGPT-5 vs GPT-5.4 Mini16 shared evalsDeepSeek V3.2 vs GPT-4.1 Mini15 shared evalsGPT-5 vs Qwen3.6 Plus15 shared evalsDeepSeek V3.2 vs GPT-4.115 shared evalsDeepSeek V3.2 vs GPT-4o-mini15 shared evalsDeepSeek V3.2 vs GPT-4.1 Nano15 shared evalsGPT-5 vs GPT-6 Astra12 shared evalsDeepSeek V3.2 vs GPT-6 Astra9 shared evals
Comparing something else? Build your own side-by-side.