Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
 Grok 4xAI |  Llama 4 ScoutMeta |  Qwen3.6-27BAlibaba |  DeepSeek-R1DeepSeek | |
|---|---|---|---|---|
| Vendor | xAI | Meta | Alibaba | DeepSeek |
| Family | Grok | Llama | Qwen | DeepSeek |
| Release date | 2025-07-09 | 2025-04-05 | 2026-04-22 | 2025-01-20 |
| Context window | 256,000 tokens | 10,000,000 tokens | 262,144 tokens | 128,000 tokens |
| Parameters | — | 109B | 27B (dense) | 671B |
| Modality | text | text, vision | text, vision, video | text |
| License | proprietary | Llama 4 Community License | Apache-2.0 | MIT |
| Source | proprietary | open weights | open weights | open weights |
| Description | — | — | Alibaba's first dense open-weight in the 3.6 family. Strong agentic-coding scores (77.2 SWE-bench Verified, matching Claude 4.5 Opus on Terminal-Bench 2.0). Supports 201 languages and multimodal text/image/video input. | Reasoning-focused open-weight model. |
| Links | ||||
| Benchmarks | ||||
| MMLU-Pro | 82.8% | — | 78.9% | — |
| GPQA-D | 87.5% | — | — | — |
| HumanEval | — | — | 91.5% | — |
| Aider | 72.5% | — | 70.2% | — |
| AIME-25 | 86.1% | — | — | 79.8% |
| LiveCB | 65.3% | — | — | — |
| MMMU | — | — | 70.3% | — |
Add a model
Claude 4.8 OpusmaxQwen3.7-Maxmax
Gemini 3.5maxGemini Omnimax
GPT-5.5maxQwen3.6-27B✓DeepSeek-V4-FlashmaxDeepSeek-V4-PromaxGemini 3 PromaxClaude 4.7 OpusmaxClaude 4.6 SonnetmaxClaude 4.5 HaikumaxDeepSeek-V3.1maxGPT-5maxGrok 4✓Gemini 2.5 FlashmaxQwen3 235Bmaxo3maxGPT-4.1maxLlama 4 Scout✓Llama 4 MaverickmaxGemini 2.5 PromaxDeepSeek-R1✓
Mistral Large 2maxMax 4 models. Remove one to add another.