Long-context Understanding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
54.19RULER Score
2
Feb 26, 2026
75.12RULER Score
2
Feb 26, 2026
0.799RULER Score
2
Feb 26, 2026
85.13RULER Score
2
Feb 26, 2026
41.45LongBench Avg (25% KV)
1
Apr 1, 2026
6,711Avg Length (English Words)
1
Apr 1, 2026