Researchers · Interviewed at COLM 2026

Muxin Liu

University of Pennsylvania

Claude vs Gemini: Same Reasoning, Different Threshold | COLM 2026

COLM 2026 · October 15, 2026 · 9 min

Claude vs Gemini: Same Reasoning, Different Threshold | COLM 2026

Is Claude really better than Gemini at catching false scientific claims? On the surface, yes. Look closer, and both models sit on the same ROC curve. Claude simply says "no" more often.

Recorded at COLM 2026 in San Francisco, this conversation features Muxin Liu, a PhD student at the University of Pennsylvania. Muxin explains why models that score high on popular scientific claim verification benchmarks still miss subtle errors, and what that means for AI for science.

More from COLM 2026

All event interviews →