update about, and new results

formatted_data.csv

@@ -22,10 +22,10 @@ prediction-online,claude-2,0.6600660066006601,200,303,1505.3135313531352,0.01334
 prediction-offline,gpt-3.5-turbo-0125,0.6578171091445427,223,339,730.1740412979351,0.0007721681415928988
 prediction-request-reasoning,gpt-3.5-turbo-0125,0.6506410256410257,203,312,1871.173076923077,0.002112727564102551
 prediction-offline-sme,gpt-3.5-turbo-0125,0.6294117647058823,214,340,1341.8323529411764,0.0014778852941176408
-prediction-request-rag,nousresearch/nous-hermes-2-mixtral-8x7b-sft,0.625,5,8,3229.375,0.0017438625
 prediction-request-reasoning,databricks/dbrx-instruct:nitro,0.5555555555555556,5,9,2257.8888888888887,0.0020320999999999664
 prediction-online,gpt-3.5-turbo-0125,0.551622418879056,187,339,1576.684365781711,0.0016928525073746164
+prediction-request-reasoning,nousresearch/nous-hermes-2-mixtral-8x7b-sft,0.535593220338983,158,295,2921.172881355932,0.0015774333559321892
+prediction-request-rag,nousresearch/nous-hermes-2-mixtral-8x7b-sft,0.5018587360594795,135,269,3099.4869888475837,0.001673722973977683
 prediction-request-rag,databricks/dbrx-instruct:nitro,0.5,5,10,2651.8,0.00238661999999997
 prediction-online-sme,gpt-3.5-turbo-0125,0.49411764705882355,168,340,2189.1882352941175,0.002402523529411752
-prediction-online,nousresearch/nous-hermes-2-mixtral-8x7b-sft,0.4666666666666667,147,315,3143.4285714285716,0.001697451428571419
-prediction-request-reasoning,nousresearch/nous-hermes-2-mixtral-8x7b-sft,0.4,4,10,2957.6,0.0015971039999999998
+prediction-online,nousresearch/nous-hermes-2-mixtral-8x7b-sft,0.4666666666666667,147,315,3143.4285714285716,0.001697451428571419

tabs/faq.py

@@ -1,8 +1,9 @@
 about_olas_predict_benchmark = """\
 How good are LLMs at making predictions about events in the future? This is a topic that hasn't been well explored to date. 
-[Olas Predict](https://olas.network/services/prediction-agents) aims to rectify this by incentivizing the creation of agents that predict the future (through prediction markets).
-This is a leaderboard showing the performance of LLM tools for making predictions (event forecasting) on a dataset, refined from Autocast.\
-The leaderboard shows tool performance in terms of accuracy and cost. \
+[Olas Predict](https://olas.network/services/prediction-agents) aims to rectify this by incentivizing the creation of agents that make predictions about future events (through prediction markets).
+These agents are tested in the wild on real-time prediction market data, which you can see on [here](https://huggingface.co/datasets/valory/prediction_market_data) on HuggingFace (updated weekly).
+However, if you want to create an agent with new tools, waiting for real-time results to arrive is slow. This is where the Olas Predict Benchmark comes in. It allows devs to backtest new approaches on a historical event forecasting dataset (refined from [Autocast](https://arxiv.org/abs/2206.15474)) with high iteration speed. While the models might be trained on some or all of the benchmark data, we can learn about the relative strengths of the different approaches (e.g models and logic), before testing the most promising ones on real-time unseen data. 
+This HF Space showcases the performance of the various models and workflows (called tools in the Olas ecosystem) for making predictions, in terms of accuracy and cost.\
 
 🤗 Pick a tool and run it on the benchmark using the "🔥 Run the Benchmark" page! 
 """
@@ -10,11 +11,8 @@ The leaderboard shows tool performance in terms of accuracy and cost. \
 about_the_tools = """\
 - [Prediction Offline](https://github.com/valory-xyz/mech/blob/main/packages/valory/customs/prediction_request/prediction_request.py) - Uses prompt engineering, but no web crawling, to make predictions
 - [Prediction Online](https://github.com/valory-xyz/mech/blob/main/packages/valory/customs/prediction_request/prediction_request.py) - Uses prompt engineering, as well as web crawling, to make predictions
-- [Prediction SME](https://github.com/valory-xyz/mech/blob/main/packages/nickcom007/customs/prediction_request_sme/prediction_request_sme.py) - Use prompt engineering to get the LLM to act as a Subject Matter Expert (SME) in making a prediction.
 - [Prediction with RAG](https://github.com/valory-xyz/mech/blob/main/packages/napthaai/customs/prediction_request_rag/prediction_request_rag.py) - Uses retrieval-augment-generation (RAG) over extracted search result to make predictions.
-- [Prediction with Research Report](https://github.com/valory-xyz/mech/blob/main/packages/polywrap/customs/prediction_with_research_report/prediction_with_research_report.py) - Generates a research report before making a prediction.
 - [Prediction with Reasoning](https://github.com/valory-xyz/mech/blob/main/packages/napthaai/customs/prediction_request_reasoning/prediction_request_reasoning.py) - Incorporates an additional call to the LLM to do reasoning over retrieved data.
-- [Prediction with CoT](https://github.com/valory-xyz/mech/blob/main/packages/napthaai/customs/prediction_url_cot/prediction_url_cot.py) - Use Chain of Thought (CoT) to make predictions.
 """
 
 about_the_dataset = """\