Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
 o3OpenAI |  DeepSeek-V3.1DeepSeek | GPT-5.6 Sol OpenAI |  Llama 4 MaverickMeta | |
|---|---|---|---|---|
| Vendor | OpenAI | DeepSeek | OpenAI | Meta |
| Family | o-series | DeepSeek | GPT | Llama |
| Release date | 2025-04-16 | 2025-08-21 | 2026-06-26 | 2025-04-05 |
| Context window | 200,000 tokens | 128,000 tokens | — | 1,000,000 tokens |
| Parameters | — | 671B | — | 400B |
| Modality | text, vision | text | text, vision, audio | text, vision |
| License | proprietary | MIT | proprietary | Llama 4 Community License |
| Source | proprietary | open weights | proprietary | open weights |
| Description | Reasoning-focused model in the o-series. | Large MoE open-weight model. Predecessor to DeepSeek-V4. | Flagship of OpenAI's GPT-5.6 three-model suite (Sol / Terra / Luna), released as a limited preview. Strong gains in coding, cybersecurity, biology, and long-horizon agentic work. Pricing: $5 / $30 per million input/output tokens. | Mixture-of-experts open-weight model from Meta. |
| Links | ||||
| Benchmarks | ||||
| MMLU-Pro | — | — | — | 80.5% |
| GPQA-D | 87.7% | — | — | — |
| AIME-25 | 88.9% | — | — | — |
| MMMU | — | — | — | 68.5% |
Add a model
GPT-5.6 Sol✓
Claude 4.8 Opusmax
Qwen3.7-Maxmax
Gemini 3.5 FlashmaxGemini 3.5maxGemini OmnimaxGPT-5.5maxDeepSeek-V4-FlashmaxGemini 3 PromaxDeepSeek-V4-PromaxQwen3.6-27BmaxClaude 4.7 OpusmaxClaude 4.6 SonnetmaxClaude 4.5 HaikumaxDeepSeek-V3.1✓GPT-5 PromaxGPT-5max
Grok 4maxGemini 2.5 FlashmaxQwen3 235Bmaxo3✓GPT-4.1maxLlama 4 ScoutmaxLlama 4 Maverick✓Gemini 2.5 PromaxDeepSeek-R1max
Mistral Large 2maxMax 4 models. Remove one to add another.