HomeEvaluation FrameworkQuality Assurance
AICPA SOC for Service Organizations
SitemapTerms of servicePrivacy policy

548 Market Street, PMB 18282, San Francisco, CA 94104

© 2026 Turing

Back to Environments

TaskForge

The TaskForge platform helps teams plan, track, and manage work by organizing tasks, projects, and workflows, supporting collaboration and visibility across development and business teams.

Overview

FeaturesCreate / Update / View, Assign & Transition, Sprint Setup…
Tasks30 prompts and verifiers
TaskForge preview
lite.taskforge.rlgym.turing.com

Leaderboard

Overall Pass Rate (pass@8)

claude-sonnet-4
34.17%
gemini-2
25.00%
gpt-computer-use-preview
11.25%

Evaluation Results

Easy: 66.7% < Pass@8 ≤ 100%

Medium: 33.3% < Pass@8 < 66.6% AND Median Steps ≤ 80

Hard: Pass@8 ≤ 33.3% OR Median Steps > 80

This model: 7 easy · 5 medium · 18 hard tasks

#1claude-sonnet-4

Pass rate: 34.17%

Capabilities

Issue Management

Create / Update / View

Manage task lifecycle.

Assign & Transition

Move task between states.

Sprint Planning

Sprint Setup

Create and manage sprints.

Backlog Grooming

Reprioritize iteams before sprint start.

Reporting

Burndown / Velocity

Track sprint progress.

Issue Analytics

Identify blockers and throughput.

Project Management

Roles & Permissions

Control team access and rights.

Workflow Configuration

Customize board stages.

Automation

Trigger Rules

Automate transitions or alerts.

Demo Execution

Watch how an AI agent interacts with this environment

Prompt

Search for the bug ticket 'Internal Server Error in Vendor Pages', create a new related bug ticket 'Update Database Port in Deployment Scripts' assigned to Emily Carter, and link it to the first using link type 'blocks'. Change the priority level of both tickets to 'Highest'. Mention the 'Frontend' team in comments section of both tickets to request QA review as '@Frontend - please review these linked bugs for QA verification'.

Loading timeline...

Back to EnvironmentsVisit Environment