Bullshit Benchmark: leaderboard
Tests whether models detect nonsense. Questions use fake precision, confident nonsense framing, cross-domain concept stitching, and other deceptive techniques. Rated green/amber/red by multiple judges.
Metric: BS Detection Rate (%). Source: petergpt.github.io. Saturation forecast: Around July 2027. 204 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 96.4 | #37 |
| 2 | Claude Sonnet 4.6 | 94.5 | #90 |
| 3 | Claude Opus 4.6 | 92.7 | #63 |
| 4 | Claude Opus 4.5 | 90.9 | #83 |
| 5 | Claude Haiku 4.5 | 87.3 | #280 |
| 6 | Qwen 3.8 Max | 87.3 | #35 |
| 7 | Claude Opus 4.7 | 80 | #49 |
| 8 | Qwen 3.8 27B | 76.4 | #105 |
| 9 | Claude Fable 5.1 | 69.1 | #9 |
| 10 | Grok 4.20 Multi-Agent | 67.3 | #113 |
| 11 | Claude Sonnet 4.5 | 65.5 | #142 |
| 12 | Qwen 3.5 397B A17B | 65.5 | #146 |
| 13 | Claude Sonnet 5 | 65.5 | #57 |
| 14 | Nemotron 3 Super | 65.5 | #335 |
| 15 | Grok 4.6 | 63.6 | #26 |
No result here: #7 GPT-6.1 Sol, #8 Gemini 4 Argon, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=bullshit-benchmark · How It Works · Data refreshed daily, snapshot 2026-10-20.