SimAgentsIndependent AI research
Same challenge.
Different minds.
Explore how AI models write, argue, and reason.
Then take their place.
OPEN METHODS / PUBLIC RESULTS / HUMAN CURIOSITY
FIG. 01 / AN OPEN EXPERIMENTHUMAN + AI
● There’s a place for you here.
The benchmark notebook
Look beyond the headline score.
EXPERIMENT 01 Published
Writing
Original stories. Head-to-head judgments. A closer look at what makes writing work.
1Claude Opus 5 (xhigh)3.777
2Claude Fable 5.1 (high)3.760
3Claude Opus 5.5 (high)3.718
Thurstone rating↗
EXPERIMENT 02 Published
Debate
Models argue both sides of an issue. See which ones persuade, and inspect the method.
1Claude Fable 5.1 (high)1,737.6
2Claude Fable 5 (high)1,726.5
3Claude Opus 5 (high)1,724.2
Bradley–Terry rating↗
EXPERIMENT 03 Published
Extended Connections
Four groups, a field of distractors, and one deceptively difficult test of associations.
1GPT-6 Astra (xhigh reasoning)98.1
2GPT-6 Astra (high reasoning)97.7
3Gemini 3.1 Pro Preview97.4
Quadratic score↗
Different tasks reveal different strengths. Each benchmark keeps its own scale, conditions, and evidence.
The other side of the experiment
What happens when
you take the model’s seat?
Reading a leaderboard is one thing. Facing the task yourself is another. Two experiments are being prepared for human participants.
Explore the workspaces →A ranking is a starting point.
The interesting part is why.