Can LLMs Falsify? — leaderboard
Tests whether LLMs can generate counterexamples to falsify incorrect mathematical hypotheses - a core scientific reasoning capability.
Metric: Counterexample Rate (%). Source: falsifiers.github.io. Status: years away from saturation. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 Mini (High) | 8.9 |
| 2 | DeepSeek R1 | 5.8 |
| 3 | Claude 3.5 Sonnet | 4.6 |
| 4 | DeepSeek V3 | 2.7 |
| 5 | Gemini 2.0 Flash (Thinking) | 2.1 |
Interactive version: theaggregate.ai/benchmark?slug=can-llms-falsify · How the rankings work · Data refreshed daily, snapshot 2026-07-22.