Compare models
Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.
Comparing agents instead? Switch to agent compare →
 Claude 4.7 OpusAnthropic |  Gemini 3 Pro |  DeepSeek-V3.1DeepSeek |  Grok 4xAI | |
|---|---|---|---|---|
| Vendor | Anthropic | DeepSeek | xAI | |
| Family | Claude | Gemini | DeepSeek | Grok |
| Release date | 2026-04-16 | 2026-04-22 | 2025-08-21 | 2025-07-09 |
| Context window | 1,000,000 tokens | 2,000,000 tokens | 128,000 tokens | 256,000 tokens |
| Parameters | — | — | 671B | — |
| Modality | text, vision | text, vision, audio, video | text | text |
| License | proprietary | proprietary | MIT | proprietary |
| Source | proprietary | proprietary | open weights | proprietary |
| Description | Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle). Optimized for complex reasoning and coding. Improved software engineering, long-running coding tasks, and higher-resolution vision over Claude 4.6. | 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. | Large MoE open-weight model. Predecessor to DeepSeek-V4. | — |
| Links | ||||
| Benchmarks | ||||
| MMLU-Pro | 88.2% | 87.1% | — | 82.8% |
| GPQA-D | 90.1% | 88.6% | — | 87.5% |
| HumanEval | 97.4% | 96.5% | — | — |
| Aider | 91.2% | 84.8% | — | 72.5% |
| AIME-25 | 93.5% | 92.8% | — | 86.1% |
| LiveCB | 80.2% | 76.1% | — | 65.3% |
| MMMU | 79.0% | 84.3% | — | — |
Add a model
Claude 4.8 Opusmax
Qwen3.7-MaxmaxGemini 3.5maxGemini Omnimax
GPT-5.5maxQwen3.6-27BmaxDeepSeek-V4-FlashmaxDeepSeek-V4-PromaxGemini 3 Pro✓Claude 4.7 Opus✓Claude 4.6 SonnetmaxClaude 4.5 HaikumaxDeepSeek-V3.1✓GPT-5maxGrok 4✓Gemini 2.5 FlashmaxQwen3 235Bmaxo3maxGPT-4.1max
Llama 4 ScoutmaxLlama 4 MaverickmaxGemini 2.5 PromaxDeepSeek-R1max
Mistral Large 2maxMax 4 models. Remove one to add another.