LLM Comparison
DeepSeek V3.2 vs MiniMind
Side-by-side specs, pricing & capabilities · Updated September 2026
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 53 157 | |
| Family | DeepSeek | MiniMind |
| Status | Current | Current |
| Release Date | Dec 2025 | Sep 2026 |
| Context Window | 164K tokens | 1K tokens |
| Input Price | $0.26/M tokens | Free |
| Output Price | $0.42/M tokens | Free |
| Pricing Notes | Cache read: $0.1350/M tokens | Open-source project; API pricing is not applicable unless a downstream host adds serving costs. |
| Capabilities | textcode | texteducationtraining |
| Training Cutoff | — | Not specified |
| Max Output | 164K tokens | 1K tokens |
| API Identifier | deepseek/deepseek-v3.2 | jingyaogong/minimind |
| Benchmarks | ||
| MMLU-Pro | 85deepseek | — |
| GPQA Diamond | 82.4deepseek | — |
| AIME 2025 | 93.1deepseek | — |
| LiveCodeBench | 83.3deepseek | — |
| SWE-bench Verified | 73.1deepseek | — |
| HLE | 25.1deepseek | — |
| BrowseComp | 51.4deepseek | — |
| View DeepSeek V3.2 | View MiniMind | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| MiniMindCheapest | $0.00 | $0.00 | $0.00 | — |
| DeepSeek V3.2 | $0.26 | $0.21 | $0.47 | +0% |
DeepSeek
DeepSeek V3.2
DeepSeek V3.2 is a large language model from DeepSeek. Supports up to 163,840 token context window. Achieves 87.1% on MMLU. Available from $0.26/M input tokens.
Jingyao Gong
MiniMind
MiniMind is a small open-source language-model training project that demonstrates how to train a 64M-parameter LLM from scratch. The repository is aimed at builders who want a compact, inspectable model-training path rather than a hosted frontier API.
More Comparisons
Looking for more AI models?
Browse All LLMs