Benchmark explainer
Basic human common-sense reasoning that resists memorized knowledge
A multiple-choice text benchmark of adversarial everyday-reasoning questions (spatio-temporal, social, and trick questions) on which unspecialized humans outperform frontier models. 213 questions total but only 10 are public; the rest are held out.
Discrimination
93.9/100Does it still separate models?
Saturation headroom
99/100How far from ceiling / clustered at the top?
Contamination resistance
100/100Public vs held-out; training-leak risk.
Harness comparability
100/100Is it apples-to-apples, or mixed / vendor-optimized?
Freshness
79/100How old is the benchmark?
Contamination history: Held-out design is the primary defense; only the 10-example sample public since 2024; no confirmed train-set leakage found
Limitations: Very small human sample (n=9); only 10 public items limits external auditability; 213 items is a small set with non-trivial per-question noise; trick-question framing may reward a specific answer style
| Model | Score | Evidence |
|---|---|---|
| Claude Fable 5.2 | 93.88 | unverified |
| Gemini 4 Carbon | 91.12 | unverified |
| Gemini 4 Argon | 90.04 | unverified |
| Claude Opus 5.5 | 86.08 | unverified |
| Claude Fable 5.1 | 83.92 | unverified |
SimpleBench: A multiple-choice text benchmark of adversarial everyday-reasoning questions (spatio-temporal, social, and trick questions) on which unspecialized humans outperform frontier models. 213 questions total but only 10 are public; the rest are held out.
Claude Fable 5.2 leads SimpleBench at 93.88. The full leaderboard above lists every recorded measurement, not just the headline number.
96 models have recorded scores on SimpleBench, spanning a score spread of 93.88.
tensor.news grades SimpleBench A for integrity (score 95.8/100), ranking #6 of 62 benchmarks we assess across discrimination, saturation, contamination resistance, harness comparability, and freshness.
No — SimpleBench still has headroom and continues to discriminate between models rather than bunching them at the ceiling.
Its test set is held-out, which lowers — but does not eliminate — the risk that training data leaked into the questions.
Scores are reported under a consistent harness, so comparisons on SimpleBench are reasonably apples-to-apples.
Every SimpleBench measurement is source-backed and tagged reproduced, self-reported, or unverified; the underlying record cites simple-bench.com.