Grok-2
xAI
xAI's state-of-the-art AI assistant with advanced text and vision understanding, integrating real-time information from the 𝕏 (Twitter) platform. Released August 2024 for 𝕏 Premium and Premium+ users. Achieves competitive performance with frontier models on graduate-level science (GPQA), general knowledge (MMLU, MMLU-Pro), and math (MATH). Excels at vision tasks - reaches 93.6% on DocVQA document Q&A (outperforming GPT-4 Turbo 87.2% and Claude 3.5 Sonnet 89.3%). Introduced as 'sus-column-r' on LMArena, outperforming Claude and GPT-4 on LMSYS leaderboard. Includes Grok-2 mini variant balancing speed and quality.
Strengths
- Real-time information integration from 𝕏 platform for current events
- Exceptional document understanding - 93.6% DocVQA (beats GPT-4 Turbo and Claude 3.5 Sonnet)
- Competitive with frontier models on academic benchmarks (GPQA, MMLU, MATH)
- Outperformed Claude and GPT-4 on LMSYS leaderboard (as 'sus-column-r')
- Advanced vision capabilities for charts, documents, and images
- Grok-2 mini variant provides speed-quality balance
- Integrated into 𝕏 Premium for seamless platform experience
Caveats
- Primarily accessible via 𝕏 Premium subscription (limited API availability)
- Real-time integration limited to 𝕏 platform data
- Newer model with less ecosystem maturity than OpenAI/Anthropic
- 4K max output tokens lower than some competitors
- API pricing and availability less standardized than major providers
- Vendor
- xAI
- Context Window
- 128,000 tokens
- Max Output
- 4,096 tokens
- License
- Proprietary
- Release Date
- 2024-08-13
- Modalities
- textimage
| Benchmark | Score | Max |
|---|---|---|
| DocVQA | 93.6 | - |
| livebench_coding | 47.1 | 100.0 |
| livebench_instruction_following | 73.7 | 100.0 |
| livebench_language | 45.5 | 100.0 |
Capabilities
Vision
Audio
Video
Tool Use
Resources
Pricing
Available via 𝕏 Premium subscription. API pricing varies by provider