DeepSeek V3.2 vs Gemini 3.5 Flash
Head to head on 21 shared benchmarks, with price, context window, and release dates.
Benchmark scores
41evals · sort by any column, ⤢ to expand fullscreen
| Model | ||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flash Google (Alphabet Inc.) | 64.7% | 26.0% | 71.8 | 39.0% | 92.2% | 42.7% | 76.3% | 78.9% | 78.2% | 64.9% | 75.6% | 84.6% | 88.2% | 82.0% | 76.3% | 31.0% | 53.1% | 74.4% | 40.9% | 48.7% | 95.3% | - | - | - | - | 1087elo | - | 57.9% | - | - | - | 55.8% | 76.6% | - | 68.1% | 49.9% | - | - | - | 53.1% | 62.9% | 64.3% |
| DeepSeek V3.2 DeepSeek | 47.9% | 16.0% | 66.8 | 22.1% | 84.0% | 24.6% | 60.7% | 65.9% | 64.6% | 50.0% | 48.2% | 70.4% | 85.0% | 77.2% | 57.5% | 8.0% | 38.9% | 68.2% | 35.6% | 5.1% | 90.6% | 74.7% | 74.2% | 92.0% | 0.0% | - | 1511elo | - | 31.3% | 68.0% | 86.2% | - | - | 86.2% | - | - | 59.0% | 70.0% | 65 | - | - | 55.4% |
2 / 2 models
| Attribute | DeepSeek V3.2 DeepSeek | Gemini 3.5 Flash Google (Alphabet Inc.) |
|---|---|---|
| Description | DeepSeek V3.2 is an AI model from DeepSeek, released with open weights. | Gemini 3.5 Flash is an AI model from Google (Alphabet Inc.). |
| Family | Deepseek | Gemini |
| Params | - | - |
| Open weights | open | closed |
| License | mit | proprietary |
| Released | 1 Dec 2025 | 19 May 2026 |
| Context | 163,840 | 1,048,576 |
| Input $/1M | $0.28 | $1.50 |
| Output $/1M | $0.42 | $9.00 |
| Cache read $/1M | $0.134 | $0.150 |
| Cache write $/1M | - | $0.083 |
| Speed | 0 tok/s | 0 tok/s |
| Latency | 0.00 s | 0.00 s |
| Modalities | text | text, image, video, file, audio |
| Providers | - | - |
| Publisher | DeepSeek | Google (Alphabet Inc.) |
| Reported scores | Aider Polyglot Benchmark74.2% (Aider) MathArena57.47% GPQA Diamond84.0% (AA) Humanity's Last Exam (HLE)24.6% (AA) | Humanity's Last Exam (HLE)42.7% (AA) τ²-bench (Tau²-bench)95.3% (AA) Terminal-Bench (Hard)40.9% (AA) Vals Index53.1% |
FAQ
- Is DeepSeek V3.2 or Gemini 3.5 Flash better?
- Across the 21 benchmarks both models report on Sophon, Gemini 3.5 Flash leads on 21 of them. Which one is "better" depends on the benchmark - the table above shows every shared score.
- How do DeepSeek V3.2 and Gemini 3.5 Flash compare on GPQA Diamond?
- DeepSeek V3.2 scores 84.0% and Gemini 3.5 Flash scores 92.2% on GPQA Diamond.
- Which is cheaper, DeepSeek V3.2 or Gemini 3.5 Flash?
- DeepSeek V3.2 is cheaper at $0.42 per million output tokens against $9.00 for Gemini 3.5 Flash - about 21.4x.
- When were DeepSeek V3.2 and Gemini 3.5 Flash released?
- DeepSeek V3.2 was released 1 Dec 2025 by DeepSeek. Gemini 3.5 Flash was released 19 May 2026 by Google (Alphabet Inc.).
Comparing something else? Build your own side-by-side.