Traditional benchmarks reward models for attempting every question, encouraging educated guesses. The Omniscience Index changes this by deducting points for wrong answers but not for "I don't know" responses. This creates an incentive for labs to train models that are less prone to factual hallucination.
Related Insights
The proliferation of AI leaderboards incentivizes companies to optimize models for specific benchmarks. This creates a risk of "acing the SATs" where models excel on tests but don't necessarily make progress on solving real-world problems. This focus on gaming metrics could diverge from creating genuine user value.
An AI that confidently provides wrong answers erodes user trust more than one that admits uncertainty. Designing for "humility" by showing confidence indicators, citing sources, or even refusing to answer is a superior strategy for building long-term user confidence and managing hallucinations.
Benchmarking revealed no strong correlation between a model's general intelligence and its tendency to hallucinate. This suggests that a model's "honesty" is a distinct characteristic shaped by its post-training recipe, not just a byproduct of having more knowledge.
The "Omniscience" accuracy benchmark, which measures pure factual knowledge, tracks more closely with a model's total parameters than any other metric. This suggests embedded knowledge is a direct function of model size, distinct from reasoning abilities developed via training techniques.
Traditional benchmarks often reward guessing. Artificial Analysis's "Omniscience Index" changes the incentive by subtracting points for wrong answers but not for "I don't know" responses. This encourages models to demonstrate calibration instead of fabricating facts.
As benchmarks become standard, AI labs optimize models to excel at them, leading to score inflation without necessarily improving generalized intelligence. The solution isn't a single perfect test, but continuously creating new evals that measure capabilities relevant to real-world user needs.
Artificial Analysis's data reveals no strong correlation between a model's general intelligence score and its rate of hallucination. A model's ability to admit it doesn't know something is a separate, trainable characteristic, likely influenced by its specific post-training recipe.
Artificial Analysis found its knowledge-based "Amnesian's" accuracy benchmark tracks closely with an LLM's total parameter count. By plotting open-weight models on this curve, they can reasonably estimate the size of closed models, suggesting leading frontier models are in the 5-10 trillion parameter range.
Traditional benchmarks incentivize guessing by only rewarding correct answers. The Omniscience Index directly combats hallucination by subtracting points for incorrect factual answers. This creates a powerful incentive for model developers to train their systems to admit when they lack knowledge, improving reliability.
An OpenAI paper argues hallucinations stem from training systems that reward models for guessing answers. A model saying "I don't know" gets zero points, while a lucky guess gets points. The proposed fix is to penalize confident errors more harshly, effectively training for "humility" over bluffing.
