YOUR RESEARCH WORKSPACE

What are we investigating?

Start with a task, a puzzling result, or a hypothesis.
Work with your agent, then let a focused study run on its own.

Enter to send · Shift + Enter for a new line. Choose your agent from the model menu.

A place to start

Choose an example and make it yours

Interactive

Work with an agent in chat. Write code, run simulations, inspect plots and steer the next experiment.

Autonomous research

Set a hypothesis and execution budget. The agent runs experiments, seeks counterexamples and submits evidence for independent review.

YOUR COMPUTE

Machines

Connect your machines. Run experiments in parallel.

The research agent stays here. Connected machines run your experiments.

YOUR AGENT, YOUR MACHINE

API connections, if you need them.

Choose your agent and model inside each conversation. Installed CLI agents need no API setup here.

SIMJECTURE BENCHMARK RESULTS

Model leaderboard

Measured scientific coding tasks. Compare completion, time and API-equivalent cost.

Results

Task leaderboard

Find a model Rank by Effort Cost basis

Cost–time Pareto plot

Upper left is better. Dashed lines connect the same model's reasoning efforts.

Methodology ↗

Published API tariffs

Your runs & community contributions

Test any supported model with your installed agent or API connection. Local and imported runs appear in Community & local. Official results are maintained by Simjecture.

Prepare or grade a task

Your benchmark conversations

Latest numerical grade

YOUR WORKBENCH

Research tools

Use what’s installed. Add a solver when your investigation needs it.

Installed 1

On this computer · includes detected local builds

Available to add 0

Install directly or prepare with your agent

Installation and readiness checks tell you a tool can run. Each investigation still validates its scientific method. For tools on SSH workers, use .

Agent

Model

Reasoning effort

AUTONOMOUS RESEARCH

PREPARE IT TOGETHER

Let your agent shape the investigation.

Your conversation and files are the starting point. The agent fills the brief; you review it before launching.

Review or edit the study details

Agree on the investigation

EDITABLE BRIEF

Your agent fills these details from the conversation. You can change them here if needed. Each launched study keeps its agreed conditions.

Question or claim to testWhat evidence would answer it?Constraints and available inputs

When is the research complete?

Time budget (hours)

Research instruments Execution machines

Choose prepared workers for parallel experiments. Register a managed local worker in Machines to include it in a pool. Worker profiles define their own experiment environment.

Execution settings

Research director · stop and replan expensive experiments

Reviews strategy while jobs run, preserves partial data on stops, and asks the worker to acknowledge a new plan. Scientific claim review stays separate.

Reviewer and director model (optional) Reviewer and director reasoning Experiment environment

Cooperative execution is for a dedicated unprivileged account and does not isolate host networking.

Runs survive closing this page. They stop at the original deadline or an independently accepted outcome. You can pause or stop them earlier.

WorkspaceFiles & live runs

Simulations 0

Commands 0

Project files

⌁

Your experiments, in view.

Ask your agent to run a simulation. Its live console and saved outputs appear here, beside the conversation. These are exploration results; independent study review is separate.

Agent commands and their output appear here.

Project files 0

Shared inputs, reports and comparisons for this conversation. Select a simulation to see its own outputs.

Project folder location

Copy large datasets here directly. Browser uploads support files up to 64 MB.

Research brief

When you’re ready, ask your agent to prepare an autonomous investigation.

Working principle

Explore freely. Keep the question explicit. Let recorded evidence and independent review decide the outcome.

What are we investigating?

A place to start

Simulate a double pendulum

Explore reconnecting magnetic islands

Does a pendulum keep the same period?

Interactive

Autonomous research

Machines

Worker jobs

Add a machine

API connections, if you need them.

Model leaderboard

Task leaderboard

Finish time ranking

Cost ranking

Cost–time Pareto plot

Prepare or grade a task

Your benchmark conversations

Research tools

Installed 1

Available to add 0

Tool details

Connect a research tool

Let your agent shape the investigation.

Agree on the investigation

Delete conversation?

Workspace details