oneshotlm
Compare all models on this prompt →

Force-directed graph · gpt-4o-mini-2024-07-18

Using the pre-provided d3.min.js (global d3), render an interactive force-directed graph of about 40 nodes in several clusters with draggable nodes, hover highlighting of neighbors, and zoom/pan. Define the sample nodes and links inline.

⛨ sandboxed Open in new tab ↗
transcript · 4 messages
user

Using the pre-provided d3.min.js (global d3), render an interactive force-directed graph of about 40 nodes in several clusters with draggable nodes, hover highlighting of neighbors, and zoom/pan. Define the sample nodes and links inline.

assistant
write index.html (4293 bytes)
toolResult

Successfully wrote 4293 bytes to index.html

assistant

The interactive force-directed graph web application has been created and written into a single file named `index.html`. You can now open this file in a web browser to view and interact with the graph.

TAKE IT TO CODE

A single self-contained HTML file — copy it and open in any browser, or reuse the prompt with your own pi-agent run.

RUN

modelgpt-4o-mini-2024-07-18
vendorOpenAI
harnesspi-agent
generated2026-08-01

EVALUATION

2/5 partial

Force graph renders with colored nodes but only ~20 visible, no clusters distinct, drag/wheel shift view drastically off-frame, no hover highlighting seen.

Vision grade · anthropic/claude-sonnet-5

MEASUREMENTS

Raw readings from the capture, not a verdict — the grade above is the only judgement. Percentages are how much of the screen changed; the measure under-reports sparse motion on a dark background.

idle motion0.0%
on click0.0%
on drag6.1%
on wheel5.9%
on enter + space0.0%
on arrow keys2.0%
on w/a/s/d0.0%
frame spread8.3 / 255
console errors0
js errors none

METRICS

runtime22.1s
tokens in3.8k
tokens out1.4k
cached2.6k
cost / run$0.0012