Motif 3 (Beta): benchmark results

Provider: Motif. Released 2026-07-14. Access: Open.

Unified ELO 1643 ± 1, rank #271 of 1761 rated models, from 15 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA Humanity's Last Exam40.36Accuracy (%)91.2
BenchmarkList ECI141.05Capability Index (ECI)90.2
Artificial Analysis Intelligence Index36.76Intelligence Index88.4
AA GPQA Diamond86.87Accuracy (%)82.2
AA CritPt6Accuracy (%)81
AA Long Context Reasoning74.67Accuracy (%)77.5
AA Omniscience-17.77Score65.7
AA GDPval1187.41ELO62.4
AA Omniscience - Science, Engineering & Mathematics30.33Accuracy (%)59.2
AA Omniscience - Law13.4Accuracy (%)57.2
AA Omniscience - Health21Accuracy (%)52.6
AA Omniscience - Software Engineering (SWE)27.4Accuracy (%)52.5

Interactive version: theaggregate.ai/model?slug=motif-3-beta · How It Works · Data refreshed daily, snapshot 2026-09-05.