Beyond AIME

Beyond AIME is a difficult mathematical reasoning benchmark designed to test deeper reasoning chains and harder decomposition than standard AIME-style problem sets.

2rows
scoreprimary metric
2026-05-06sampled

Metadata

Metrics

Score, Normalized Score

Latest Results

Rank Subject Score Model Match Provenance Sampled
1 Sarvam-105B 0.69 Self-reported 2026-05-06
2 Sarvam-30B 0.58 Self-reported 2026-05-06