LLM Comparison
DiffusionGemma vs MiniCPM
Side-by-side specs, pricing & capabilities · Updated June 2026
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 38 | |
| Family | Gemma | MiniCPM |
| Status | Current | Current |
| Release Date | Jun 2026 | — |
| Context Window | 256K tokens | 128K tokens |
| Input Price | Free | Free |
| Output Price | Free | Free |
| Pricing Notes | Open-weights model under Apache 2.0; API pricing depends on the host or local infrastructure used. | Open-weight GitHub and Hugging Face model family. There is no fixed vendor API price; runtime cost depends on the host, hardware, or inference provider. |
| Capabilities | textvisioncodereasoninglocal-inference | textcodereasoninglocal-inference |
| Training Cutoff | — | Not publicly specified in queued source |
| Max Output | 256 tokens | 33K tokens |
| API Identifier | google/diffusiongemma-26b-a4b-it | OpenBMB/MiniCPM |
| Benchmarks | ||
| MMLU Pro | 77.6official-google-model-card | — |
| GPQA Diamond | 73.2official-google-model-card | — |
| LiveCodeBench v6 | 69.1official-google-model-card | — |
| MMMLU | 81.5official-google-model-card | — |
| HLE no tools | 11official-google-model-card | — |
| MiniCPM-SALA standard benchmark average | — | 76.53official-github-readme |
| MiniCPM-SALA long-context average | — | 38.97official-github-readme |
| MiniCPM-SALA 2048K extrapolation score | — | 81.6official-github-readme |
| MiniCPM4.1 reasoning decoding speedup | — | 3official-github-readme |
| MiniCPM4 Jetson AGX Orin decoding speedup vs Qwen3-8B | — | 7official-github-readme |
| View DiffusionGemma | View MiniCPM | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| DiffusionGemmaCheapest | $0.00 | $0.00 | $0.00 | — |
| MiniCPMCheapest | $0.00 | $0.00 | $0.00 | — |
DiffusionGemma
DiffusionGemma is Google DeepMind’s experimental open-weights text-diffusion model based on Gemma 4 26B A4B. It uses discrete diffusion and parallel canvas denoising to trade some benchmark quality for much faster local generation on dedicated GPUs.
OpenBMB
MiniCPM
MiniCPM is OpenBMB’s ultra-efficient open language-model family for edge and end-device deployment. The MiniCPM4 and MiniCPM4.1 lines focus on fast local reasoning, while MiniCPM-SALA extends the family toward sparse/linear attention and million-token context research.
More Comparisons
Looking for more AI models?
Browse All LLMs