Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
 Gemini 3.5 Flash |  DeepSeek-V3.1DeepSeek |  Grok 4xAI | |
|---|---|---|---|
| Vendor | DeepSeek | xAI | |
| Family | Gemini | DeepSeek | Grok |
| Release date | 2026-05-20 | 2025-08-21 | 2025-07-09 |
| Context window | — | 128,000 tokens | 256,000 tokens |
| Parameters | — | 671B | — |
| Modality | text, vision, audio | text | text |
| License | proprietary | MIT | proprietary |
| Source | proprietary | open weights | proprietary |
| Description | Fast, low-cost tier of the Gemini 3.5 family announced at Google I/O 2026. June 2026 update added native computer-use capability, moving Flash from generation to agentic task execution. | Large MoE open-weight model. Predecessor to DeepSeek-V4. | — |
| Links | |||
| Benchmarks | |||
| MMLU-Pro | — | — | 82.8% |
| GPQA-D | — | — | 87.5% |
| Aider | — | — | 72.5% |
| AIME-25 | — | — | 86.1% |
| LiveCB | — | — | 65.3% |
Add a model
GPT-5.6 Sol+
Claude 4.8 Opus+
Qwen3.7-Max+Gemini 3.5 Flash✓Gemini 3.5+Gemini Omni+GPT-5.5+DeepSeek-V4-Flash+Gemini 3 Pro+DeepSeek-V4-Pro+Qwen3.6-27B+Claude 4.7 Opus+Claude 4.6 Sonnet+Claude 4.5 Haiku+DeepSeek-V3.1✓GPT-5 Pro+GPT-5+Grok 4✓Gemini 2.5 Flash+Qwen3 235B+o3+GPT-4.1+
Llama 4 Scout+Llama 4 Maverick+Gemini 2.5 Pro+DeepSeek-R1+
Mistral Large 2+