Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
 DeepSeek-V4-FlashDeepSeek |  Llama 4 MaverickMeta | DeepSeek-V3.1 DeepSeek |  Gemini 3 Pro | |
|---|---|---|---|---|
| Vendor | DeepSeek | Meta | DeepSeek | |
| Family | DeepSeek | Llama | DeepSeek | Gemini |
| Release date | 2026-04-22 | 2025-04-05 | 2025-08-21 | 2026-04-22 |
| Context window | 1,000,000 tokens | 1,000,000 tokens | 128,000 tokens | 2,000,000 tokens |
| Parameters | 284B (13B active) | 400B | 671B | — |
| Modality | text | text, vision | text | text, vision, audio, video |
| License | MIT | Llama 4 Community License | MIT | proprietary |
| Source | open weights | open weights | open weights | proprietary |
| Description | Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE. | Mixture-of-experts open-weight model from Meta. | Large MoE open-weight model. Predecessor to DeepSeek-V4. | Google DeepMind's flagship multimodal model. Best-in-class for multimodal understanding and agentic / vibe coding workflows. A "Deep Think" reasoning mode is available to AI Ultra subscribers. |
| Links | ||||
| Benchmarks | ||||
| MMLU-Pro | — | 80.5% | — | 87.1% |
| GPQA-D | — | — | — | 88.6% |
| HumanEval | — | — | — | 96.5% |
| Aider | — | — | — | 84.8% |
| AIME-25 | — | — | — | 92.8% |
| LiveCB | — | — | — | 76.1% |
| MMMU | — | 68.5% | — | 84.3% |
Add a model
Claude 4.8 Opusmax
Qwen3.7-MaxmaxGemini 3.5maxGemini Omnimax
GPT-5.5maxQwen3.6-27BmaxDeepSeek-V4-Flash✓DeepSeek-V4-PromaxGemini 3 Pro✓Claude 4.7 OpusmaxClaude 4.6 SonnetmaxClaude 4.5 HaikumaxDeepSeek-V3.1✓GPT-5max
Grok 4maxGemini 2.5 FlashmaxQwen3 235Bmaxo3maxGPT-4.1maxLlama 4 ScoutmaxLlama 4 Maverick✓Gemini 2.5 PromaxDeepSeek-R1max
Mistral Large 2maxMax 4 models. Remove one to add another.