import gradio as gr from gradio_leaderboard import Leaderboard, SelectColumns, ColumnFilter import config from envs import RESULTS_REPO_ID, REPO_ID, API, HF_TOKEN from pathlib import Path import pandas as pd import os import json from utils.viz import create_scatter_plot, create_flow_chart, create_bar_chart, create_task_success_heatmap, create_leaderboard from utils.processing import check_and_process_uploads from huggingface_hub import snapshot_download from apscheduler.schedulers.background import BackgroundScheduler from datetime import datetime import json import re import markdown import asyncio from apscheduler.schedulers.asyncio import AsyncIOScheduler # import weave from utils.db import TracePreprocessor from gradio.themes.soft import Soft preprocessor = TracePreprocessor() from datetime import datetime abs_path = Path(__file__).parent def restart_space(): API.restart_space(repo_id=REPO_ID, token=HF_TOKEN) # New function to download results def download_latest_results(): print("Downloading latest results...") snapshot_download(RESULTS_REPO_ID, local_dir= "evals_upload", repo_type='dataset', tqdm_class=None, etag_timeout=30, max_workers=4, ) print("Download complete.") def get_analyzed_traces(agent_name, benchmark_name): return preprocessor.get_analyzed_traces(agent_name, benchmark_name) def get_failure_report(agent_name, benchmark_name): return preprocessor.get_failure_report(agent_name, benchmark_name) def parse_json_files(folder_path, benchmark_name, aggregate=True): return preprocessor.get_parsed_results(benchmark_name, aggregate=aggregate) def update_agent_dropdown(benchmark_name, metric): df = parse_json_files(os.path.join(abs_path, "evals_live"), benchmark_name) agents = df['Agent Name'].tolist() best_agent = get_best_agent(benchmark_name, metric) return gr.Dropdown(choices=agents, value=best_agent, label="Select Agent") def get_best_agent(benchmark_name, metric): df = parse_json_files(os.path.join(abs_path, "evals_live"), benchmark_name) return df.loc[df[metric].idxmax()]['Agent Name'] def update_task_analysis(benchmark_name, agent_name): if not agent_name: return "Please select an agent.", None, None, "" analyzed_traces = get_analyzed_traces(agent_name, benchmark_name) if not analyzed_traces: return f"No analysis available for agent: {agent_name}", None, None, "" task_ids = list(analyzed_traces.keys()) overview, flow_chart, _ = update_task_details(benchmark_name, agent_name, task_ids[0]) return overview, flow_chart, gr.Dropdown(choices=task_ids, value=task_ids[0], label="Select Task"), "" def update_task_details(benchmark_name, agent_name, task_id): if not task_id: return "Please select a task.", None, "" analyzed_traces = get_analyzed_traces(agent_name, benchmark_name) if not analyzed_traces or task_id not in analyzed_traces: return f"No analysis available for task: {task_id}", None, "" analysis = analyzed_traces[task_id] summary = analysis.get('task_analysis', {}) overview = f"### Summary\n\n{summary.get('overview', 'No overview available.')}\n\n" # overview += f"### Successes\n{summary.get('key_successes', 'No successes listed.')}\n\n" # overview += f"### Challenges\n{summary.get('main_challenges', 'No challenges listed.')}\n\n" # overview += f"### Overall Assessment\n{summary.get('overall_assessment', 'No assessment available.')}\n\n" if summary.get('overview', 'No overview available.') != "Not available": flow_chart = create_flow_chart(analysis['steps']) else: flow_chart = None return overview, flow_chart, "" def format_call_info(step, step_index): call_data = step['call_data'] analysis = step['analysis'] def format_json(obj): # if isinstance(obj, dict) and 'choices' in obj: # # Special handling for message content # formatted_content = format_message_content(obj['choices'][0]) # return f'
{formatted_content}
' # else: json_str = json.dumps(obj, indent=2) json_str = json_str.replace(' ', ' ') json_str = json_str.replace('\n', '
') return f'
{json_str}
' # Currently not used but we can enable it to format message content def format_message_content(content): # Convert Markdown to HTML html_content = markdown.markdown(content) # Replace ``` code blocks with styled pre blocks html_content = re.sub(r'```python\n(.*?)```', lambda m: f'
{m.group(1)}
', html_content, flags=re.DOTALL) return html_content formatted_info = f"""

Step {step_index + 1}: {analysis.get('headline', '')}

Call Metadata

Inputs

{format_json(call_data['inputs'])}

Outputs

{format_json(call_data['outputs'])}

Usage

{format_json(call_data['summary'])}

Analysis

""" return formatted_info def update_failure_report(agent_name, benchmark_name): failure_report = get_failure_report(agent_name, benchmark_name) if not failure_report: return "No failure report available for this agent.", None # Create overview of failure categories categories_overview = "### Failure Categories:\n\n" for category in failure_report['failure_categories']: categories_overview += f"#### {category['category_name']}\n" categories_overview += f"{category['description']}\n\n" # Count tasks affected by each category category_counts = {} for task, classification in failure_report['task_classifications'].items(): category_id = classification['category_id'] category_counts[category_id] = category_counts.get(category_id, 0) + 1 # Prepare data for bar chart categories = [cat['category_name'] for cat in failure_report['failure_categories']] counts = [category_counts.get(str(i+1), 0) for i in range(len(categories))] # Create bar chart chart = create_bar_chart(categories, counts, "Failure Categories", "Number of Affected Tasks", "Failure Categories Distribution") return categories_overview, chart from gradio.themes.utils import colors, fonts, sizes from typing import Iterable class MyTheme(Soft): def __init__( self, *, primary_hue: colors.Color | str = colors.blue, text_size: sizes.Size | str = sizes.text_lg, font: fonts.Font | str | Iterable[fonts.Font | str] = ( fonts.GoogleFont("Lato"), "ui-sans-serif", "sans-serif", ), font_mono: fonts.Font | str | Iterable[fonts.Font | str] = ( fonts.GoogleFont("IBM Plex Mono"), "ui-monospace", "monospace", ), ): super().__init__( primary_hue=primary_hue, text_size=text_size, font=font, font_mono=font_mono, ) my_theme = MyTheme() with gr.Blocks(theme=my_theme, css='css.css', title="HAL: Holistic Agent Leaderboard") as demo: # gr.Markdown((Path(__file__).parent / "header.md").read_text(), elem_classes=["text-large"]) gr.HTML("""

Holistic Agent Leaderboard (HAL)

A standardized, cost-aware, and third-party leaderboard for evaluating agents.

""") gr.HTML("""
Standardized

Evaluations across agent benchmarks are all recorded to a single leaderboard that evaluates every listed agent in the same way.

Cost-controlled

For downstream users, understanding the cost of running agents is a significant need for adoption. For agent developers, cost-controlled evaluations help develop accurate baselines.

Third-party

Agent developers clearly have competing objectives in reporting accuracy: they want to achieve state-of-the-art performance.

Who is it for?

We see HAL being useful for four types of users:

Downstream Users & Procurers

Customers looking to deploy agents can get visibility into existing benchmarks, know developers building useful agents, and identify the state of the art for both cost and accuracy for their tasks of interest.

Leaderboards

Agent Benchmark Developers

Reporting results on a centralized leaderboard could allow improved visibility into agent benchmarks that measure real-world utility.

Add a Benchmark

Agent Developers

HAL allows for easy reproduction of past agents, clear comparison with past baselines, and a straightforward way to compete on a leaderboard.

Submit an Agent Leaderboards Reproduction Guide

Safety Researchers

Understanding agent capabilities on real-world safety threats and their associated costs is crucial. For example, Cybench evaluations could provide insights into agent performance and affordability for potential adversaries.

Cybench Leaderboard (coming soon) Agent Monitor

Leaderboards

Select a benchmark to see the agent leaderboard. Verified results have been run by the HAL team:

""") with gr.Tabs() as tabs: with gr.Tab("CORE-Bench"): gr.HTML("""

CORE-Bench evaluates the ability of agents to computationally reproduce the results of published scientific papers. Agents are given the codebase of a paper and must install all libraries and dependencies, run the code, and read through the output and figures to answer questions about the paper. The benchmark has tasks at three difficulty levels:

""") with gr.Tab("CORE-Bench-Hard"): gr.HTML("""

CORE-Bench-Hard: The agent is given the codebase of the paper and must install all libraries and dependencies, run the code, and read through the output and figures to answer questions about the paper. This level is most akin to fully reproducing a paper and is the most realistic and challenging level.

""") with gr.Row(): with gr.Column(scale=2): Leaderboard( value=create_leaderboard(parse_json_files(os.path.join(abs_path, "evals_live"), 'corebench_hard'), ci_metrics=["Accuracy", "Total Cost"]), select_columns=SelectColumns( default_selection=config.COREBENCH_ON_LOAD_COLUMNS + ["Verified"], cant_deselect=["Agent Name"], label="Select Columns to Display:", ), hide_columns=config.COREBENCH_HIDE_COLUMNS, search_columns=config.COREBENCH_SEARCH_COLUMNS, ) # gr.Markdown("""*Error ranges span from the lowest to highest observed values in repeated runs.*""", elem_classes=["text-right"]) with gr.Row(): gr.Markdown("### Accuracy vs. Cost on CORE-Bench-Hard") with gr.Row(): scatter_plot = gr.Plot(create_scatter_plot(parse_json_files(os.path.join(abs_path, "evals_live"), 'corebench_hard', aggregate=False), "Total Cost", "Accuracy", "Total Cost (in USD)", "Accuracy", ["Agent Name"])) gr.HTML('
') gr.Markdown("## Task success heatmap") gr.Markdown("The task success heatmap shows which agent can solve which tasks. Agents are sorted by total accuracy (higher is better); tasks in USACO are sorted by decreasing order of difficulty (tasks on the left are solved by the most agents; tasks on the right are solved by the least. For agents that have been run more than once, the run with the highest score is shown.") with gr.Row(): task_success_heatmap = gr.Plot() demo.load( lambda: create_task_success_heatmap( preprocessor.get_task_success_data('corebench_hard'), 'CORE-Bench-Hard' ), outputs=[task_success_heatmap] ) with gr.Tab("CORE-Bench-Medium"): gr.HTML("""

CORE-Bench-Medium: The agent is given a Dockerfile and instructions on how to use the Dockerfile to fully reproduce the paper. This level mainly evaluates agents ability to use and interact with the terminal. The agent must then answer questions about the output of the code, as in the above level.

""") with gr.Row(): with gr.Column(scale=2): Leaderboard( value=create_leaderboard(parse_json_files(os.path.join(abs_path, "evals_live"), 'corebench_medium'), ci_metrics=["Accuracy", "Total Cost"]), select_columns=SelectColumns( default_selection=config.COREBENCH_ON_LOAD_COLUMNS + ["Verified"], cant_deselect=["Agent Name"], label="Select Columns to Display:", ), hide_columns=config.COREBENCH_HIDE_COLUMNS, search_columns=config.COREBENCH_SEARCH_COLUMNS, ) # gr.Markdown("""*Error ranges span from the lowest to highest observed values in repeated runs.*""", elem_classes=["text-right"]) with gr.Row(): gr.Markdown("### Accuracy vs. Cost on CORE-Bench-Medium") with gr.Row(): scatter_plot = gr.Plot(create_scatter_plot(parse_json_files(os.path.join(abs_path, "evals_live"), 'corebench_medium', aggregate=False), "Total Cost", "Accuracy", "Total Cost (in USD)", "Accuracy", ["Agent Name"])) gr.HTML('
') gr.Markdown("## Task success heatmap") gr.Markdown("The task success heatmap shows which agent can solve which tasks. Agents are sorted by total accuracy (higher is better); tasks in USACO are sorted by decreasing order of difficulty (tasks on the left are solved by the most agents; tasks on the right are solved by the least. For agents that have been run more than once, the run with the highest score is shown.") with gr.Row(): task_success_heatmap = gr.Plot() demo.load( lambda: create_task_success_heatmap( preprocessor.get_task_success_data('corebench_medium'), 'CORE-Bench-Medium' ), outputs=[task_success_heatmap] ) with gr.Tab("CORE-Bench-Easy"): gr.HTML("""

CORE-Bench-Easy: The agent is given the output of the code and must answer questions about the output without running any code. To answer questions, agents must navigate through the terminal output as well as files and figures generated by the code.

""") with gr.Row(): with gr.Column(scale=2): Leaderboard( value=create_leaderboard(parse_json_files(os.path.join(abs_path, "evals_live"), 'corebench_easy'), ci_metrics=["Accuracy", "Total Cost"]), select_columns=SelectColumns( default_selection=config.COREBENCH_ON_LOAD_COLUMNS + ["Verified"], cant_deselect=["Agent Name"], label="Select Columns to Display:", ), hide_columns=config.COREBENCH_HIDE_COLUMNS, search_columns=config.COREBENCH_SEARCH_COLUMNS, ) # gr.Markdown("""*Error ranges span from the lowest to highest observed values in repeated runs.*""", elem_classes=["text-right"]) with gr.Row(): gr.Markdown("### Accuracy vs. Cost on CORE-Bench-Easy") with gr.Row(): scatter_plot = gr.Plot(create_scatter_plot(parse_json_files(os.path.join(abs_path, "evals_live"), 'corebench_easy', aggregate=False), "Total Cost", "Accuracy", "Total Cost (in USD)", "Accuracy", ["Agent Name"])) gr.HTML('
') gr.Markdown("## Task success heatmap") gr.Markdown("The task success heatmap shows which agent can solve which tasks. Agents are sorted by total accuracy (higher is better); tasks in USACO are sorted by decreasing order of difficulty (tasks on the left are solved by the most agents; tasks on the right are solved by the least. For agents that have been run more than once, the run with the highest score is shown.") with gr.Row(): task_success_heatmap = gr.Plot() demo.load( lambda: create_task_success_heatmap( preprocessor.get_task_success_data('corebench_easy'), 'CORE-Bench-Easy' ), outputs=[task_success_heatmap] ) gr.Markdown((Path(__file__).parent / "agent_submission_core.md").read_text()) with gr.Tab("USACO"): gr.Markdown("""The USA Computing Olympiad (USACO) is a computer programming competition for pre-college students. This benchmark evaluates the performance of AI agents on a set of 307 USACO tasks. The agents are evaluated based on the number of tasks correctly solved.""") with gr.Row(): with gr.Column(scale=2): Leaderboard( value=create_leaderboard(parse_json_files(os.path.join(abs_path, "evals_live"), 'usaco'), ci_metrics=["Accuracy", "Total Cost"]), select_columns=SelectColumns( default_selection=config.USACO_ON_LOAD_COLUMNS + ["Verified"], cant_deselect=["Agent Name"], label="Select Columns to Display:", ), hide_columns=config.USACO_HIDE_COLUMNS, search_columns=config.USACO_SEARCH_COLUMNS, ) gr.Markdown("""*Error ranges span from the lowest to highest observed values in repeated runs.*""", elem_classes=["text-right"]) with gr.Row(): gr.Markdown("### Accuracy vs. Cost for USACO agents") with gr.Row(): scatter_plot = gr.Plot(create_scatter_plot(parse_json_files(os.path.join(abs_path, "evals_live"), 'usaco', aggregate=False), "Total Cost", "Accuracy", "Total Cost (in USD)", "Accuracy", ["Agent Name"])) gr.HTML('
') gr.Markdown("## Task success heatmap") gr.Markdown("The task success heatmap shows which agent can solve which tasks. Agents are sorted by total accuracy (higher is better); tasks in USACO are sorted by decreasing order of difficulty (tasks on the left are solved by the most agents; tasks on the right are solved by the least. For agents that have been run more than once, the run with the highest score is shown.") with gr.Row(): task_success_heatmap = gr.Plot() demo.load( lambda: create_task_success_heatmap( preprocessor.get_task_success_data('usaco'), 'USACO' ), outputs=[task_success_heatmap] ) gr.HTML(""" """) with gr.Group(elem_classes=["grouped-section"]): gr.Markdown("# Agent monitor", elem_classes=["grouped-section-title"], elem_id="agent-monitor") gr.Markdown('The agent monitor provides an overview of the recurring errors an agent makes as well as a summary of the steps the agent takes to solve a task. It currently consists of two main components:') gr.HTML('
') gr.Markdown("## Failure report for each agent") gr.Markdown('Select an agent to see why the agent fails to solve tasks correctly. Note that these descriptions (and the failure categories) are generated by LLM-based evaluations of the agent logs and may contain inaccuracies.') gr.HTML('
') with gr.Row(): with gr.Column(scale=1): failure_report_agent_dropdown = gr.Dropdown(label="Select Agent for Failure Report") gr.HTML('
') with gr.Row(): with gr.Column(scale=1): failure_categories_overview = gr.Markdown() with gr.Column(scale=1): failure_categories_chart = gr.Plot() # Initialize the failure report agent dropdown with all agents demo.load(update_agent_dropdown, inputs=[gr.Textbox(value="usaco", visible=False), gr.Textbox(value="Accuracy", visible=False)], outputs=[failure_report_agent_dropdown]) # Update failure report when agent is selected failure_report_agent_dropdown.change(update_failure_report, inputs=[failure_report_agent_dropdown, gr.Textbox(value="usaco", visible=False)], outputs=[failure_categories_overview, failure_categories_chart]) gr.HTML('
') gr.Markdown("## Task overview") gr.HTML('
') with gr.Row(): with gr.Column(scale=1): agent_dropdown = gr.Dropdown(label="Select Agent") with gr.Column(scale=1): task_dropdown = gr.Dropdown(label="Select USACO Task") gr.HTML('
') with gr.Row(): task_overview = gr.Markdown() with gr.Row(): flow_chart = gr.Plot(label="Task Flow") # Initialize the agent dropdown with the best agent demo.load(update_agent_dropdown, inputs=[gr.Textbox(value="usaco", visible=False), gr.Textbox(value="Accuracy", visible=False)], outputs=[agent_dropdown]) demo.load(update_task_analysis, inputs=[gr.Textbox(value="usaco", visible=False), agent_dropdown], outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) agent_dropdown.change(update_task_analysis, inputs=[gr.Textbox(value="usaco", visible=False), agent_dropdown], outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) task_dropdown.change(update_task_details, inputs=[gr.Textbox(value="usaco", visible=False), agent_dropdown, task_dropdown], outputs=[task_overview, flow_chart, gr.Textbox(visible=False)]) gr.Markdown("## Raw predictions") gr.Markdown('Select an agent to see the raw predictions made by the agent for each task. We also provide information on token usage for each call.') with gr.Accordion("Expand to inspect raw predictions of agents...", open=False): with gr.Row(): with gr.Column(scale=1): raw_agent_dropdown = gr.Dropdown(label="Select Agent") with gr.Column(scale=1): raw_task_dropdown = gr.Dropdown(label="Select Task") with gr.Column(scale=1): raw_step_dropdown = gr.Dropdown(label="Select Step") with gr.Row(): raw_call_details = gr.HTML() def update_raw_task_dropdown(agent_name): analyzed_traces = get_analyzed_traces(agent_name, "usaco") if not analyzed_traces: return gr.Dropdown(choices=[], label="Select Task"), gr.Dropdown(choices=[], label="Select Step"), f"No raw predictions data available for agent: {agent_name}." task_ids = list(analyzed_traces.keys()) steps = analyzed_traces[task_ids[0]]['steps'] return gr.Dropdown(choices=task_ids, label="Select Task", value=task_ids[0]), gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(get_analyzed_traces(agent_name, "usaco")[task_ids[0]]['steps'][0], 0) def update_raw_step_dropdown(agent_name, task_id): analyzed_traces = get_analyzed_traces(agent_name, "usaco") if not analyzed_traces or task_id not in analyzed_traces: return gr.Dropdown(choices=[], label="Select Step", value="No data available.") steps = analyzed_traces[task_id]['steps'] return gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(steps[0], 0) def update_raw_call_details(agent_name, task_id, step_index): analyzed_traces = get_analyzed_traces(agent_name, "usaco") if not analyzed_traces or task_id not in analyzed_traces: return "No data available for this selection." steps = analyzed_traces[task_id]['steps'] if step_index is None: return "Invalid step selection." step = steps[step_index] return format_call_info(step, step_index) # Initialize the raw agent dropdown with all agents demo.load(update_agent_dropdown, inputs=[gr.Textbox(value="usaco", visible=False), gr.Textbox(value="Accuracy", visible=False)], outputs=[raw_agent_dropdown]) demo.load(update_raw_task_dropdown, inputs=[raw_agent_dropdown], outputs=[raw_task_dropdown, raw_step_dropdown]) demo.load(update_raw_call_details, inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], outputs=[raw_call_details]) raw_agent_dropdown.change(update_raw_task_dropdown, inputs=[raw_agent_dropdown], outputs=[raw_task_dropdown, raw_step_dropdown, raw_call_details]) raw_task_dropdown.change(update_raw_step_dropdown, inputs=[raw_agent_dropdown, raw_task_dropdown], outputs=[raw_step_dropdown, raw_call_details]) raw_step_dropdown.change(update_raw_call_details, inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], outputs=[raw_call_details]) with gr.Tab("SWE-bench Verified (Mini)"): gr.Markdown("""SWE-bench is a dataset that tests systems' ability to solve GitHub issues automatically. Verified is a human-validated subset of 500 problems reviewed by software engineers. The We are currently actively developing this platform and this benchmark is not fully implemented yet.""") with gr.Row(): with gr.Column(scale=2): Leaderboard( value=create_leaderboard(parse_json_files(os.path.join(abs_path, "evals_live"), 'swebench_verified_mini'), ci_metrics=["Accuracy", "Total Cost"]), select_columns=SelectColumns( default_selection=config.SWEBENCH_ON_LOAD_COLUMNS + ["Verified"], cant_deselect=["Agent Name"], label="Select Columns to Display:", ), hide_columns=config.SWEBENCH_HIDE_COLUMNS, search_columns=config.SWEBENCH_SEARCH_COLUMNS, ) gr.Markdown("""*Error ranges span from the lowest to highest observed values in repeated runs.*""", elem_classes=["text-right"]) with gr.Row(): gr.Markdown("### Accuracy vs. Cost for SWE-bench agents") with gr.Row(): scatter_plot = gr.Plot(create_scatter_plot(parse_json_files(os.path.join(abs_path, "evals_live"), 'swebench_verified_mini', aggregate=False), "Total Cost", "Accuracy", "Total Cost (in USD)", "Accuracy", ["Agent Name"])) gr.HTML('
') gr.Markdown("## Task success heatmap") gr.Markdown("The task success heatmap shows which agent can solve which tasks. Agents are sorted by total accuracy (higher is better); tasks in SWE-bench are sorted by decreasing order of difficulty (tasks on the left are solved by the most agents; tasks on the right are solved by the least. For agents that have been run more than once, the run with the highest score is shown.") with gr.Row(): task_success_heatmap = gr.Plot() demo.load( lambda: create_task_success_heatmap( preprocessor.get_task_success_data('swebench_verified_mini'), 'SWE-bench Verified (Mini)' ), outputs=[task_success_heatmap] ) # gr.HTML(""" # # """) # with gr.Group(elem_classes=["grouped-section"]): # gr.Markdown("# Agent monitor", elem_classes=["grouped-section-title"], elem_id="agent-monitor") # gr.HTML('
') # gr.Markdown("## Failure report for each agent") # gr.Markdown('Select an agent to see why the agent fails to solve tasks correctly. Note that these descriptions (and the failure categories) are generated by LLM-based evaluations of the agent logs and may contain inaccuracies.') # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # failure_report_agent_dropdown = gr.Dropdown(label="Select Agent for Failure Report") # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # failure_categories_overview = gr.Markdown() # with gr.Column(scale=1): # failure_categories_chart = gr.Plot() # # Initialize the failure report agent dropdown with all agents # demo.load(update_agent_dropdown, # inputs=[gr.Textbox(value="swebench_verified", visible=False), gr.Textbox(value="Accuracy", visible=False)], # outputs=[failure_report_agent_dropdown]) # # Update failure report when agent is selected # failure_report_agent_dropdown.change(update_failure_report, # inputs=[failure_report_agent_dropdown, gr.Textbox(value="swebench_verified", visible=False)], # outputs=[failure_categories_overview, failure_categories_chart]) # gr.HTML('
') # gr.Markdown("## Task overview") # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # agent_dropdown = gr.Dropdown(label="Select Agent") # with gr.Column(scale=1): # task_dropdown = gr.Dropdown(label="Select SWE-bench Verified Task") # gr.HTML('
') # with gr.Row(): # task_overview = gr.Markdown() # with gr.Row(): # flow_chart = gr.Plot(label="Task Flow") # # Initialize the agent dropdown with the best agent # demo.load(update_agent_dropdown, inputs=[gr.Textbox(value="swebench_verified", visible=False), gr.Textbox(value="Accuracy", visible=False)], outputs=[agent_dropdown]) # demo.load(update_task_analysis, inputs=[gr.Textbox(value="swebench_verified", visible=False), agent_dropdown], outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) # agent_dropdown.change(update_task_analysis, # inputs=[gr.Textbox(value="swebench_verified", visible=False), agent_dropdown], # outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) # task_dropdown.change(update_task_details, # inputs=[gr.Textbox(value="swebench_verified", visible=False), agent_dropdown, task_dropdown], # outputs=[task_overview, flow_chart, gr.Textbox(visible=False)]) gr.Markdown("## Raw predictions") gr.Markdown('Select an agent to see the raw predictions made by the agent for each task. We also provide information on token usage for each call.') with gr.Accordion("Expand to inspect raw predictions of agents...", open=False): with gr.Row(): with gr.Column(scale=1): raw_agent_dropdown = gr.Dropdown(label="Select Agent") with gr.Column(scale=1): raw_task_dropdown = gr.Dropdown(label="Select Task") with gr.Column(scale=1): raw_step_dropdown = gr.Dropdown(label="Select Step") with gr.Row(): raw_call_details = gr.HTML() def update_raw_task_dropdown(agent_name): analyzed_traces = get_analyzed_traces(agent_name, "swebench_verified_mini") if not analyzed_traces: return gr.Dropdown(choices=[], label="Select Task"), gr.Dropdown(choices=[], label="Select Step"), f"No raw predictions data available for agent: {agent_name}." task_ids = list(analyzed_traces.keys()) steps = analyzed_traces[task_ids[0]]['steps'] return gr.Dropdown(choices=task_ids, label="Select Task", value=task_ids[0]), gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(get_analyzed_traces(agent_name, "swebench_verified_mini")[task_ids[0]]['steps'][0], 0) def update_raw_step_dropdown(agent_name, task_id): analyzed_traces = get_analyzed_traces(agent_name, "swebench_verified_mini") if not analyzed_traces or task_id not in analyzed_traces: return gr.Dropdown(choices=[], label="Select Step", value="No data available.") steps = analyzed_traces[task_id]['steps'] return gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(steps[0], 0) def update_raw_call_details(agent_name, task_id, step_index): analyzed_traces = get_analyzed_traces(agent_name, "swebench_verified_mini") if not analyzed_traces or task_id not in analyzed_traces: return "No data available for this selection." steps = analyzed_traces[task_id]['steps'] if step_index is None: return "Invalid step selection." step = steps[step_index] return format_call_info(step, step_index) # Initialize the raw agent dropdown with all agents demo.load(update_agent_dropdown, inputs=[gr.Textbox(value="swebench_verified_mini", visible=False), gr.Textbox(value="Accuracy", visible=False)], outputs=[raw_agent_dropdown]) demo.load(update_raw_task_dropdown, inputs=[raw_agent_dropdown], outputs=[raw_task_dropdown, raw_step_dropdown]) demo.load(update_raw_call_details, inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], outputs=[raw_call_details]) raw_agent_dropdown.change(update_raw_task_dropdown, inputs=[raw_agent_dropdown], outputs=[raw_task_dropdown, raw_step_dropdown, raw_call_details]) raw_task_dropdown.change(update_raw_step_dropdown, inputs=[raw_agent_dropdown, raw_task_dropdown], outputs=[raw_step_dropdown, raw_call_details]) raw_step_dropdown.change(update_raw_call_details, inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], outputs=[raw_call_details]) with gr.Tab("SWE-bench Verified"): gr.Markdown("""SWE-bench is a dataset that tests systems' ability to solve GitHub issues automatically. Verified is a human-validated subset of 500 problems reviewed by software engineers. The We are currently actively developing this platform and this benchmark is not fully implemented yet.""") with gr.Row(): with gr.Column(scale=2): Leaderboard( value=create_leaderboard(parse_json_files(os.path.join(abs_path, "evals_live"), 'swebench_verified'), ci_metrics=["Accuracy", "Total Cost"]), select_columns=SelectColumns( default_selection=config.SWEBENCH_ON_LOAD_COLUMNS + ["Verified"], cant_deselect=["Agent Name"], label="Select Columns to Display:", ), hide_columns=config.SWEBENCH_HIDE_COLUMNS, search_columns=config.SWEBENCH_SEARCH_COLUMNS, ) gr.Markdown("""*Error ranges span from the lowest to highest observed values in repeated runs.*""", elem_classes=["text-right"]) with gr.Row(): gr.Markdown("### Accuracy vs. Cost for SWE-bench agents") with gr.Row(): scatter_plot = gr.Plot(create_scatter_plot(parse_json_files(os.path.join(abs_path, "evals_live"), 'swebench_verified', aggregate=False), "Total Cost", "Accuracy", "Total Cost (in USD)", "Accuracy", ["Agent Name"])) gr.HTML('
') gr.Markdown("## Task success heatmap") gr.Markdown("The task success heatmap shows which agent can solve which tasks. Agents are sorted by total accuracy (higher is better); tasks in SWE-bench are sorted by decreasing order of difficulty (tasks on the left are solved by the most agents; tasks on the right are solved by the least. For agents that have been run more than once, the run with the highest score is shown.") with gr.Row(): task_success_heatmap = gr.Plot() demo.load( lambda: create_task_success_heatmap( preprocessor.get_task_success_data('swebench_verified'), 'SWE-bench Verified' ), outputs=[task_success_heatmap] ) # gr.HTML(""" # # """) # with gr.Group(elem_classes=["grouped-section"]): # gr.Markdown("# Agent monitor", elem_classes=["grouped-section-title"], elem_id="agent-monitor") # gr.HTML('
') # gr.Markdown("## Failure report for each agent") # gr.Markdown('Select an agent to see why the agent fails to solve tasks correctly. Note that these descriptions (and the failure categories) are generated by LLM-based evaluations of the agent logs and may contain inaccuracies.') # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # failure_report_agent_dropdown = gr.Dropdown(label="Select Agent for Failure Report") # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # failure_categories_overview = gr.Markdown() # with gr.Column(scale=1): # failure_categories_chart = gr.Plot() # # Initialize the failure report agent dropdown with all agents # demo.load(update_agent_dropdown, # inputs=[gr.Textbox(value="swebench_verified", visible=False), gr.Textbox(value="Accuracy", visible=False)], # outputs=[failure_report_agent_dropdown]) # # Update failure report when agent is selected # failure_report_agent_dropdown.change(update_failure_report, # inputs=[failure_report_agent_dropdown, gr.Textbox(value="swebench_verified", visible=False)], # outputs=[failure_categories_overview, failure_categories_chart]) # gr.HTML('
') # gr.Markdown("## Task overview") # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # agent_dropdown = gr.Dropdown(label="Select Agent") # with gr.Column(scale=1): # task_dropdown = gr.Dropdown(label="Select SWE-bench Verified Task") # gr.HTML('
') # with gr.Row(): # task_overview = gr.Markdown() # with gr.Row(): # flow_chart = gr.Plot(label="Task Flow") # # Initialize the agent dropdown with the best agent # demo.load(update_agent_dropdown, inputs=[gr.Textbox(value="swebench_verified", visible=False), gr.Textbox(value="Accuracy", visible=False)], outputs=[agent_dropdown]) # demo.load(update_task_analysis, inputs=[gr.Textbox(value="swebench_verified", visible=False), agent_dropdown], outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) # agent_dropdown.change(update_task_analysis, # inputs=[gr.Textbox(value="swebench_verified", visible=False), agent_dropdown], # outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) # task_dropdown.change(update_task_details, # inputs=[gr.Textbox(value="swebench_verified", visible=False), agent_dropdown, task_dropdown], # outputs=[task_overview, flow_chart, gr.Textbox(visible=False)]) gr.Markdown("## Raw predictions") gr.Markdown('Select an agent to see the raw predictions made by the agent for each task. We also provide information on token usage for each call.') with gr.Accordion("Expand to inspect raw predictions of agents...", open=False): with gr.Row(): with gr.Column(scale=1): raw_agent_dropdown = gr.Dropdown(label="Select Agent") with gr.Column(scale=1): raw_task_dropdown = gr.Dropdown(label="Select Task") with gr.Column(scale=1): raw_step_dropdown = gr.Dropdown(label="Select Step") with gr.Row(): raw_call_details = gr.HTML() def update_raw_task_dropdown(agent_name): analyzed_traces = get_analyzed_traces(agent_name, "swebench_verified") if not analyzed_traces: return gr.Dropdown(choices=[], label="Select Task"), gr.Dropdown(choices=[], label="Select Step"), f"No raw predictions data available for agent: {agent_name}." task_ids = list(analyzed_traces.keys()) steps = analyzed_traces[task_ids[0]]['steps'] return gr.Dropdown(choices=task_ids, label="Select Task", value=task_ids[0]), gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(get_analyzed_traces(agent_name, "swebench_verified")[task_ids[0]]['steps'][0], 0) def update_raw_step_dropdown(agent_name, task_id): analyzed_traces = get_analyzed_traces(agent_name, "swebench_verified") if not analyzed_traces or task_id not in analyzed_traces: return gr.Dropdown(choices=[], label="Select Step", value="No data available.") steps = analyzed_traces[task_id]['steps'] return gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(steps[0], 0) def update_raw_call_details(agent_name, task_id, step_index): analyzed_traces = get_analyzed_traces(agent_name, "swebench_verified") if not analyzed_traces or task_id not in analyzed_traces: return "No data available for this selection." steps = analyzed_traces[task_id]['steps'] if step_index is None: return "Invalid step selection." step = steps[step_index] return format_call_info(step, step_index) # Initialize the raw agent dropdown with all agents demo.load(update_agent_dropdown, inputs=[gr.Textbox(value="swebench_verified", visible=False), gr.Textbox(value="Accuracy", visible=False)], outputs=[raw_agent_dropdown]) demo.load(update_raw_task_dropdown, inputs=[raw_agent_dropdown], outputs=[raw_task_dropdown, raw_step_dropdown]) demo.load(update_raw_call_details, inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], outputs=[raw_call_details]) raw_agent_dropdown.change(update_raw_task_dropdown, inputs=[raw_agent_dropdown], outputs=[raw_task_dropdown, raw_step_dropdown, raw_call_details]) raw_task_dropdown.change(update_raw_step_dropdown, inputs=[raw_agent_dropdown, raw_task_dropdown], outputs=[raw_step_dropdown, raw_call_details]) raw_step_dropdown.change(update_raw_call_details, inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], outputs=[raw_call_details]) # with gr.Tab("SWE-bench Lite"): # gr.Markdown("""SWE-bench is a dataset that tests systems' ability to solve GitHub issues automatically. Lite is a subset of 300 tasks of the original SWE-bench. We are currently actively developing this platform and this benchmark is not fully implemented yet.""") # with gr.Row(): # with gr.Column(scale=2): # Leaderboard( # value=create_leaderboard(parse_json_files(os.path.join(abs_path, "evals_live"), 'swebench_lite'), ci_metrics=["Accuracy", "Total Cost"]), # select_columns=SelectColumns( # default_selection=config.SWEBENCH_ON_LOAD_COLUMNS + ["Verified"], # cant_deselect=["Agent Name"], # label="Select Columns to Display:", # ), # hide_columns=config.SWEBENCH_HIDE_COLUMNS, # search_columns=config.SWEBENCH_SEARCH_COLUMNS, # ) # gr.Markdown("""*Error ranges span from the lowest to highest observed values in repeated runs.*""", elem_classes=["text-right"]) # with gr.Row(): # gr.Markdown("### Accuracy vs. Cost for SWE-bench agents") # with gr.Row(): # scatter_plot = gr.Plot(create_scatter_plot(parse_json_files(os.path.join(abs_path, "evals_live"), 'swebench_lite', aggregate=False), "Total Cost", "Accuracy", "Total Cost (in USD)", "Accuracy", ["Agent Name"])) # gr.HTML('
') # gr.Markdown("## Task success heatmap") # gr.Markdown("The task success heatmap shows which agent can solve which tasks. Agents are sorted by total accuracy (higher is better); tasks in SWE-bench are sorted by decreasing order of difficulty (tasks on the left are solved by the most agents; tasks on the right are solved by the least. For agents that have been run more than once, the run with the highest score is shown.") # with gr.Row(): # task_success_heatmap = gr.Plot() # demo.load( # lambda: create_task_success_heatmap( # preprocessor.get_task_success_data('swebench_lite'), # 'SWE-bench Lite' # ), # outputs=[task_success_heatmap] # ) # gr.HTML(""" # # """) # with gr.Group(elem_classes=["grouped-section"]): # gr.Markdown("# Agent monitor", elem_classes=["grouped-section-title"], elem_id="agent-monitor") # gr.HTML('
') # gr.Markdown("## Failure report for each agent") # gr.Markdown('Select an agent to see why the agent fails to solve tasks correctly. Note that these descriptions (and the failure categories) are generated by LLM-based evaluations of the agent logs and may contain inaccuracies.') # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # failure_report_agent_dropdown = gr.Dropdown(label="Select Agent for Failure Report") # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # failure_categories_overview = gr.Markdown() # with gr.Column(scale=1): # failure_categories_chart = gr.Plot() # # Initialize the failure report agent dropdown with all agents # demo.load(update_agent_dropdown, # inputs=[gr.Textbox(value="swebench_lite", visible=False), gr.Textbox(value="Accuracy", visible=False)], # outputs=[failure_report_agent_dropdown]) # # Update failure report when agent is selected # failure_report_agent_dropdown.change(update_failure_report, # inputs=[failure_report_agent_dropdown, gr.Textbox(value="swebench_lite", visible=False)], # outputs=[failure_categories_overview, failure_categories_chart]) # gr.HTML('
') # gr.Markdown("## Task overview") # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # agent_dropdown = gr.Dropdown(label="Select Agent") # with gr.Column(scale=1): # task_dropdown = gr.Dropdown(label="Select SWE-bench Lite Task") # gr.HTML('
') # with gr.Row(): # task_overview = gr.Markdown() # with gr.Row(): # flow_chart = gr.Plot(label="Task Flow") # # Initialize the agent dropdown with the best agent # demo.load(update_agent_dropdown, inputs=[gr.Textbox(value="swebench_lite", visible=False), gr.Textbox(value="Accuracy", visible=False)], outputs=[agent_dropdown]) # demo.load(update_task_analysis, inputs=[gr.Textbox(value="swebench_lite", visible=False), agent_dropdown], outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) # agent_dropdown.change(update_task_analysis, # inputs=[gr.Textbox(value="swebench_lite", visible=False), agent_dropdown], # outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) # task_dropdown.change(update_task_details, # inputs=[gr.Textbox(value="swebench_lite", visible=False), agent_dropdown, task_dropdown], # outputs=[task_overview, flow_chart, gr.Textbox(visible=False)]) # gr.Markdown("## Raw predictions") # gr.Markdown('Select an agent to see the raw predictions made by the agent for each task. We also provide information on token usage for each call.') # with gr.Accordion("Expand to inspect raw predictions of agents...", open=False): # with gr.Row(): # with gr.Column(scale=1): # raw_agent_dropdown = gr.Dropdown(label="Select Agent") # with gr.Column(scale=1): # raw_task_dropdown = gr.Dropdown(label="Select Task") # with gr.Column(scale=1): # raw_step_dropdown = gr.Dropdown(label="Select Step") # with gr.Row(): # raw_call_details = gr.HTML() # def update_raw_task_dropdown(agent_name): # analyzed_traces = get_analyzed_traces(agent_name, "swebench_lite") # if not analyzed_traces: # return gr.Dropdown(choices=[], label="Select Task"), gr.Dropdown(choices=[], label="Select Step"), f"No raw predictions data available for agent: {agent_name}." # task_ids = list(analyzed_traces.keys()) # steps = analyzed_traces[task_ids[0]]['steps'] # return gr.Dropdown(choices=task_ids, label="Select Task", value=task_ids[0]), gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(get_analyzed_traces(agent_name, "swebench_lite")[task_ids[0]]['steps'][0], 0) # def update_raw_step_dropdown(agent_name, task_id): # analyzed_traces = get_analyzed_traces(agent_name, "swebench_lite") # if not analyzed_traces or task_id not in analyzed_traces: # return gr.Dropdown(choices=[], label="Select Step", value="No data available.") # steps = analyzed_traces[task_id]['steps'] # return gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(steps[0], 0) # def update_raw_call_details(agent_name, task_id, step_index): # analyzed_traces = get_analyzed_traces(agent_name, "swebench_lite") # if not analyzed_traces or task_id not in analyzed_traces: # return "No data available for this selection." # steps = analyzed_traces[task_id]['steps'] # if step_index is None: # return "Invalid step selection." # step = steps[step_index] # return format_call_info(step, step_index) # # Initialize the raw agent dropdown with all agents # demo.load(update_agent_dropdown, # inputs=[gr.Textbox(value="swebench_lite", visible=False), gr.Textbox(value="Accuracy", visible=False)], # outputs=[raw_agent_dropdown]) # demo.load(update_raw_task_dropdown, # inputs=[raw_agent_dropdown], # outputs=[raw_task_dropdown, raw_step_dropdown]) # demo.load(update_raw_call_details, # inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], # outputs=[raw_call_details]) # raw_agent_dropdown.change(update_raw_task_dropdown, # inputs=[raw_agent_dropdown], # outputs=[raw_task_dropdown, raw_step_dropdown, raw_call_details]) # raw_task_dropdown.change(update_raw_step_dropdown, # inputs=[raw_agent_dropdown, raw_task_dropdown], # outputs=[raw_step_dropdown, raw_call_details]) # raw_step_dropdown.change(update_raw_call_details, # inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], # outputs=[raw_call_details]) # with gr.Tab("MLAgentBench"): # gr.Markdown("""MLAgentBench is a suite of end-to-end Machine Learning (ML) experimentation tasks, where the agent aims to take a given dataset and a machine learning task description and autonomously develop or improve an ML model. We are currently actively developing this platform and this benchmark is not fully implemented yet. In particular, we only include one agent and a subset of tasks for this benchmark.""") # with gr.Row(): # with gr.Column(scale=2): # Leaderboard( # value=create_leaderboard(parse_json_files(os.path.join(abs_path, "evals_live"), 'mlagentbench')), # select_columns=SelectColumns( # default_selection=config.MLAGENTBENCH_ON_LOAD_COLUMNS + ["Verified"], # cant_deselect=["Agent Name"], # label="Select Columns to Display:", # ), # hide_columns=config.MLAGENTBENCH_HIDE_COLUMNS, # search_columns=config.MLAGENTBENCH_SEARCH_COLUMNS, # ) # gr.Markdown("""*Error ranges span from the lowest to highest observed values in repeated runs.*""", elem_classes=["text-right"]) # with gr.Row(): # gr.Markdown("### Accuracy vs. Cost for MLAgentBench agents") # with gr.Row(): # scatter_plot = gr.Plot(create_scatter_plot(parse_json_files(os.path.join(abs_path, "evals_live"), 'mlagentbench', aggregate=False), "Total Cost", "Overall Score", "Total Cost (in USD)", "Overall Score", ["Agent Name"])) # # gr.HTML('
') # # gr.Markdown("## Task success heatmap") # # gr.Markdown("The task success heatmap shows which agent can solve which tasks. Agents are sorted by total accuracy (higher is better); tasks in USACO are sorted by decreasing order of difficulty (tasks on the left are solved by the most agents; tasks on the right are solved by the least. For agents that have been run more than once, the run with the highest score is shown.") # # with gr.Row(): # # task_success_heatmap = gr.Plot() # # demo.load( # # lambda: create_task_success_heatmap( # # preprocessor.get_task_success_data('usaco'), # # 'USACO' # # ), # # outputs=[task_success_heatmap] # # ) # gr.HTML(""" # # """) # with gr.Group(elem_classes=["grouped-section"]): # gr.Markdown("# Agent monitor", elem_classes=["grouped-section-title"], elem_id="agent-monitor") # # gr.HTML('
') # # gr.Markdown("## Failure report for each agent") # # gr.Markdown('Select an agent to see why the agent fails to solve tasks correctly. Note that these descriptions (and the failure categories) are generated by LLM-based evaluations of the agent logs and may contain inaccuracies.') # # gr.HTML('
') # # with gr.Row(): # # with gr.Column(scale=1): # # failure_report_agent_dropdown = gr.Dropdown(label="Select Agent for Failure Report") # # gr.HTML('
') # # with gr.Row(): # # with gr.Column(scale=1): # # failure_categories_overview = gr.Markdown() # # with gr.Column(scale=1): # # failure_categories_chart = gr.Plot() # # # Initialize the failure report agent dropdown with all agents # # demo.load(update_agent_dropdown, # # inputs=[gr.Textbox(value="mlagentbench", visible=False), gr.Textbox(value="Overall Score", visible=False)], # # outputs=[failure_report_agent_dropdown]) # # # Update failure report when agent is selected # # failure_report_agent_dropdown.change(update_failure_report, # # inputs=[failure_report_agent_dropdown, gr.Textbox(value="mlagentbench", visible=False)], # # outputs=[failure_categories_overview, failure_categories_chart]) # gr.HTML('
') # gr.Markdown("## Task overview") # gr.HTML('
') # with gr.Row(): # with gr.Column(scale=1): # agent_dropdown = gr.Dropdown(label="Select Agent") # with gr.Column(scale=1): # task_dropdown = gr.Dropdown(label="Select MLAgentBench Task") # gr.HTML('
') # with gr.Row(): # task_overview = gr.Markdown() # with gr.Row(): # flow_chart = gr.Plot(label="Task Flow") # # Initialize the agent dropdown with the best agent # demo.load(update_agent_dropdown, inputs=[gr.Textbox(value="mlagentbench", visible=False), gr.Textbox(value="Overall Score", visible=False)], outputs=[agent_dropdown]) # demo.load(update_task_analysis, inputs=[gr.Textbox(value="mlagentbench", visible=False), agent_dropdown], outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) # agent_dropdown.change(update_task_analysis, # inputs=[gr.Textbox(value="mlagentbench", visible=False), agent_dropdown], # outputs=[task_overview, flow_chart, task_dropdown, gr.Textbox(visible=False)]) # task_dropdown.change(update_task_details, # inputs=[gr.Textbox(value="mlagentbench", visible=False), agent_dropdown, task_dropdown], # outputs=[task_overview, flow_chart, gr.Textbox(visible=False)]) # gr.Markdown("## Raw predictions") # gr.Markdown('Select an agent to see the raw predictions made by the agent for each task. We also provide information on token usage for each call.') # with gr.Accordion("Expand to inspect raw predictions of agents...", open=False): # with gr.Row(): # with gr.Column(scale=1): # raw_agent_dropdown = gr.Dropdown(label="Select Agent") # with gr.Column(scale=1): # raw_task_dropdown = gr.Dropdown(label="Select Task") # with gr.Column(scale=1): # raw_step_dropdown = gr.Dropdown(label="Select Step") # with gr.Row(): # raw_call_details = gr.HTML() # def update_raw_task_dropdown(agent_name): # analyzed_traces = get_analyzed_traces(agent_name, "mlagentbench") # if not analyzed_traces: # return gr.Dropdown(choices=[], label="Select Task"), gr.Dropdown(choices=[], label="Select Step"), f"No raw predictions data available for agent: {agent_name}." # task_ids = list(analyzed_traces.keys()) # steps = analyzed_traces[task_ids[0]]['steps'] # return gr.Dropdown(choices=task_ids, label="Select Task", value=task_ids[0]), gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(get_analyzed_traces(agent_name, "mlagentbench")[task_ids[0]]['steps'][0], 0) # def update_raw_step_dropdown(agent_name, task_id): # analyzed_traces = get_analyzed_traces(agent_name, "mlagentbench") # if not analyzed_traces or task_id not in analyzed_traces: # return gr.Dropdown(choices=[], label="Select Step", value="No data available.") # steps = analyzed_traces[task_id]['steps'] # return gr.Dropdown(choices=[(f"Step {i+1}", i) for i in range(len(steps))], label="Select Step", value=0), format_call_info(steps[0], 0) # def update_raw_call_details(agent_name, task_id, step_index): # analyzed_traces = get_analyzed_traces(agent_name, "mlagentbench") # if not analyzed_traces or task_id not in analyzed_traces: # return "No data available for this selection." # steps = analyzed_traces[task_id]['steps'] # if step_index is None: # return "Invalid step selection." # step = steps[step_index] # return format_call_info(step, step_index) # # Initialize the raw agent dropdown with all agents # demo.load(update_agent_dropdown, # inputs=[gr.Textbox(value="mlagentbench", visible=False), gr.Textbox(value="Overall Score", visible=False)], # outputs=[raw_agent_dropdown]) # demo.load(update_raw_task_dropdown, # inputs=[raw_agent_dropdown], # outputs=[raw_task_dropdown, raw_step_dropdown]) # demo.load(update_raw_call_details, # inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], # outputs=[raw_call_details]) # raw_agent_dropdown.change(update_raw_task_dropdown, # inputs=[raw_agent_dropdown], # outputs=[raw_task_dropdown, raw_step_dropdown, raw_call_details]) # raw_task_dropdown.change(update_raw_step_dropdown, # inputs=[raw_agent_dropdown, raw_task_dropdown], # outputs=[raw_step_dropdown, raw_call_details]) # raw_step_dropdown.change(update_raw_call_details, # inputs=[raw_agent_dropdown, raw_task_dropdown, raw_step_dropdown], # outputs=[raw_call_details]) with gr.Tab("About"): gr.Markdown((Path(__file__).parent / "about.md").read_text()) # Will trigger autoscaling of plots when tabs are switched tabs.select(fn=None, inputs=None, outputs=None, js=""" function() { setTimeout(function() { window.dispatchEvent(new Event('resize')); }, 100); } """) gr.HTML("""

How to add an agent to HAL leaderboards?

""") gr.Markdown((Path(__file__).parent / "agent_submission.md").read_text()) gr.HTML("""

How to add a benchmark to HAL?

""") gr.Markdown((Path(__file__).parent / "benchmark_submission.md").read_text()) gr.HTML("""

How can I run evaluations?

""") gr.Markdown("""Coming soon...""") async def main(): # Preprocess traces # preprocessor = TracePreprocessor() # preprocessor.preprocess_traces('evals_live') # preprocessor = TracePreprocessor() # Download the results from the Hugging Face Hub # await asyncio.to_thread(download_latest_results) # # Check for new uploads and process them # await check_and_process_uploads() scheduler = AsyncIOScheduler() scheduler.add_job(restart_space, "interval", hours=1) # scheduler.add_job(download_latest_results, "interval", hours=1) # scheduler.add_job(check_and_process_uploads, "interval", hours=1) scheduler.start() await demo.launch(favicon_path="hal.png") if __name__ == "__main__": # weave.init(f'leaderboard_{datetime.now().strftime("%Y%m%d%H%M%S")}') asyncio.run(main())