SimpleBench
Trick questions about the everyday world where humans score in the eighties — spatio-temporal reasoning, social intelligence and adversarial phrasing.
Hard, novel problems: graduate science, abstract puzzles, expert exams. One of 6 comparable tests in reasoning, a category the Index averages.
Publisher: SimpleBench / LM CouncilWhat a model is asked to do
Answer everyday trick questions about the physical and social world that most people find easy.
For exampleSofia puts an ice cube in a hot pan and leaves the kitchen for an hour. When she comes back and looks in the pan, what does she see?
Why it matters. Common sense about the real world is where fluent models still trip. People score in the eighties here.
The example is original and illustrative, not an item from the dataset.
- Models scored here
- 46
- Who produced the numbers
- Official leaderboard
- Best published result
- 81.9%
- License
- CC BY 4.0 (via Epoch AI)
- Direction
- Higher is better
- Scale
- Published as a share of items solved. For the Index, each score is a share of the best published result (81.9%), so the frontier reads 100. Guessing earns nothing on this test, so no chance correction applies.
- Provenance
- Produced by the benchmark's own leaderboard or a third-party evaluator, not by the model's maker.
Snapshot September 8, 2026
Ranking on this test
46 models on SimpleBench
Best published run per model, and how close each one comes to the best published result on this test (the frontier reads 100). Every number links to the publisher that produced it. Internal runs are marked and carry their run details on the model page.
The best models, ranked here, working inside Theo.
28 of the models on this page run inside Theo today. Theo picks the right one for each step and always shows which engine answered.