AI models agreed with each other more than with reality in a new test
Image by AI AI models agreed with each other more than with reality in a new testScience Prediction Universe found that pooling rankings improved average results, while shared scientific errors survived. By Liam 'Akiba'...
Bitcoin 1 Minute
An important story is making waves across the blockchain ecosystem. Image by AI AI models agreed with each other more than with reality in a new testScience Prediction Universe found that pooling rankings improved average results, while shared scientific errors survived. By Liam 'Akiba' Wright Editor-in-Chief Nov. 15, 2026 at 6:40 am GMT 2 min read Quick Take 01 SPU tested 13 agent configurations, finding stronger agreement between agents than with measured outcomes across public ranking tasks.
02 Pooling rankings improved scores on 73 of 100 public tasks; the authors say shared errors can remain. 03 Unequal coverage, a small private sample and no human baseline limit what the study establishes about scientific ability. Make preferred on Share Share AI models agreed more closely with one another than with laboratory measurements in a new test of AI predictions.
Market Dynamics
Pooling their rankings improved results on average, but several systems could still share the same mistake. The Science Prediction Universe study, led by UniPat AI and submitted to arXiv on Nov. 11, tested 13 agent configurations spanning 12 models on 100 public tasks and 16 private tasks.
Each configuration combined a model, reasoning setting and agent software. The study asked them to rank specified experiments across chemistry, materials science, biology and medicine. Science Prediction Universe researchers reported that, on the public tasks, average agreement between scored configurations reached a Spearman rank correlation of 0.
33 against measured outcomes. Agreement between agents exceeded their correlation with measurements on 81 of the 100 tasks. These averages use available scored predictions, with coverage varying by configuration.
Market Impact
Those figures describe how closely orderings match, rather than percentages of answers correct. Agents might rank reaction conditions by yield or materials by conductivity without having to predict numerical values. A perfect ordering without measurement ties scores 1; random rankings average 0.
Related ReadingGoogle’s new AI reveals hidden genetic clues in new immune-cell test Consensus improved predictionsThe researchers found a benefit to pooling predictions. Averaging each experiment's position across configurations produced a consensus ranking that scored 0. 08 points above the average submission, improving results on 73 of the 100 public tasks.
The reported 95% confidence interval for the gain was 0. On one oncology task, eleven configurations agreed at 0. 9 but averaged just 0.
Crypto markets are watching this development closely as investors weigh its potential impact on prices.




