🌐 Website | 📄 Paper | 🤗 Dataset
Evergreen, contamination-free, real-world, domain-specific AI evaluation framework
xbench is more than just a scoreboard — it's a new evaluation framework with two complementary tracks, designed to measure both the intelligence frontier and real-world utility of AI systems:
We open source the dataset and evaluation code for two of our AGI Tracking benchmarks: ScienceQA and DeepSearch.
DeepSearch is part of xbench's AGI Tracking series, focused on evaluating tool usage capabilities in search and information retrieval scenarios. For detailed evaluation procedures and further information, please refer to the website and Eval Card xbench-DeepSearch (Chinese version)
| Rank | Model | Mode | Company | Accuracy | Evaluation Date |
|---|---|---|---|---|---|
| 1 | o3 | Search | OpenAI | 65+ | 2025.05 |
| 2 | o4-mini-high | Search | OpenAI | 60+ | 2025.05 |
| 3 | Doubao | Deep Think | ByteDance | 50+ | 2025.05 |
| 3 | Grok-3 | DeeperSearch | xAI | 50+ | 2025.05 |
| 3 | Gemini 2.5 Pro (preview) | Deep Research | 50+ | 2025.05 |
Benchmark data is encrypted to prevent search engine crawling and contamination, please refer to the decrypt code in xbench_evals github repo to get the plain text data. Please don't upload the plain text online.
If you are developing an AI agent and would like to evaluate it using the latest version of xbench, we welcome you to contact us. Please submit a public access link of your agent, and we will complete the evaluation within an agreed timeframe and share the results with you promptly.
Contact: [email protected]
🌐 Website | 📄 Paper | 🤗 Dataset
Evergreen, contamination-free, real-world, domain-specific AI evaluation framework
xbench is more than just a scoreboard — it's a new evaluation framework with two complementary tracks, designed to measure both the intelligence frontier and real-world utility of AI systems:
We open source the dataset and evaluation code for two of our AGI Tracking benchmarks: ScienceQA and DeepSearch.
DeepSearch is part of xbench's AGI Tracking series, focused on evaluating tool usage capabilities in search and information retrieval scenarios. For detailed evaluation procedures and further information, please refer to the website and Eval Card xbench-DeepSearch (Chinese version)
| Rank | Model | Mode | Company | Accuracy | Evaluation Date |
|---|---|---|---|---|---|
| 1 | o3 | Search | OpenAI | 65+ | 2025.05 |
| 2 | o4-mini-high | Search | OpenAI | 60+ | 2025.05 |
| 3 | Doubao | Deep Think | ByteDance | 50+ | 2025.05 |
| 3 | Grok-3 | DeeperSearch | xAI | 50+ | 2025.05 |
| 3 | Gemini 2.5 Pro (preview) | Deep Research | 50+ | 2025.05 |
Benchmark data is encrypted to prevent search engine crawling and contamination, please refer to the decrypt code in xbench_evals github repo to get the plain text data. Please don't upload the plain text online.
If you are developing an AI agent and would like to evaluate it using the latest version of xbench, we welcome you to contact us. Please submit a public access link of your agent, and we will complete the evaluation within an agreed timeframe and share the results with you promptly.
Contact: [email protected]
