List your company

Scientific Idea Generation on Scientific Ideas Human Evaluation

96.67Novelty Win RateEvoScientist
65.4773.5781.6789.77Mar 9, 2026

Evaluation results

MethodLinks
EvoScientistSystem Category=Commercial Systems, Baseline Comparison=K-Dense, Evaluator=Human Experts2026.0396.673.33053.3326.67204043.3316.6753.3443.333.3350.84
EvoScientistSystem Category=Commercial Systems, Baseline Comparison=Novix, Evaluator=Human Experts2026.0393.3306.6756.676.6636.6736.67603.3373.331016.6749.17
EvoScientistSystem Category=Open-sourced Systems, Baseline Comparison=AI Scientist-v2, Evaluator=Human Experts2026.0373.331016.675016.6733.3343.33506.6753.332026.6734.16
EvoScientistSystem Category=Open-sourced Systems, Baseline Comparison=InternAgent, Evaluator=Human Experts2026.0366.6723.331096.673.3309001093.336.67084.17