DeepSeek V3.2 vs Gemini 2.5 Pro
Head to head on 21 shared benchmarks, with price, context window, and release dates.
Benchmark scores
45evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 2.5 Pro Google (Alphabet Inc.) | 83.1% | 87.7% | 60.8% | 1419elo | 58.8 | 14.1% | 84.4% | 22.5% | 48.7% | 77.9% | 86.7% | 81.0% | 65.9% | 80.1% | 86.2% | 42.8% | 53.6% | 72.9% | 26.5% | 0.4% | 54.1% | - | 88.7% | 50.4% | - | - | 45.2% | 15.9% | - | - | - | - | - | 96.7% | - | 50.6% | 73.6% | 68.9% | 70.0% | - | 41.9% | 55.6 | - | - | 53.3% | 59.5% |
| DeepSeek V3.2 DeepSeek | 74.2% | 59.0% | 47.9% | 1511elo | 66.8 | 22.1% | 75.1% | 11.2% | 49.0% | 65.9% | 64.6% | 48.2% | 70.4% | 59.3% | 83.7% | 38.7% | 70.0% | 68.2% | 32.6% | 5.1% | 78.9% | 74.7% | - | - | 0.0% | 16.0% | - | - | 31.3% | 68.0% | 50.0% | 85.0% | 77.2% | - | 57.5% | - | - | - | - | 8.0% | - | - | 59.0% | 65 | - | 51.7% |
2 / 2 models
| Attribute | DeepSeek V3.2 DeepSeek | Gemini 2.5 Pro Google (Alphabet Inc.) |
|---|---|---|
| Description | DeepSeek V3.2 is an AI model from DeepSeek, released with open weights. | Gemini 2.5 Pro is an AI model from Google (Alphabet Inc.). |
| Family | Deepseek | Gemini |
| Params | - | - |
| Open weights | open | closed |
| License | mit | proprietary |
| Released | 1 Dec 2025 | 5 Jun 2025 |
| Context | 163,840 | 1,048,576 |
| Input $/1M | $0.28 | $1.25 |
| Output $/1M | $0.42 | $10.00 |
| Cache read $/1M | $0.130 | $0.125 |
| Cache write $/1M | - | $0.375 |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text | text, image, file, audio, video |
| Providers | - | - |
| Publisher | DeepSeek | Google (Alphabet Inc.) |
| 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 Gemini 2.5 Pro better?
- Across the 21 benchmarks both models report on Sophon, Gemini 2.5 Pro leads on 12 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do DeepSeek V3.2 and Gemini 2.5 Pro compare on GPQA Diamond?
- DeepSeek V3.2 scores 75.1% and Gemini 2.5 Pro scores 84.4% on GPQA Diamond.
- Which is cheaper, DeepSeek V3.2 or Gemini 2.5 Pro?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $10.00 for Gemini 2.5 Pro - about 23.8x.
- When were DeepSeek V3.2 and Gemini 2.5 Pro released?
- DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek. Gemini 2.5 Pro was released 5 Jun 2025 by Google (Alphabet Inc.).
Comparing something else? Build your own side-by-side.