Natural Language Inference
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.797MSTPS
5
Apr 15, 2026
32.3Accuracy
5
Apr 15, 2026
3,011Total Running Time (s)
5
Feb 26, 2026
8,835Total Latency (s)
5
Feb 26, 2026
6,462Max Memory (MB)
5
Feb 26, 2026
58.7KLUE NLI Score
5
Feb 26, 2026
81.3RTE
5
Feb 26, 2026
88.28Precision
5
Feb 26, 2026
0.9NN
5
Feb 26, 2026
51.4Accuracy
5
Feb 26, 2026
67.5Exact Match
5
Feb 27, 2026
0.736Accuracy
5
Feb 26, 2026
41.5Accuracy
5
Feb 26, 2026
83.5Genetic Score
5
Feb 26, 2026
91.4Upward Acc
5
Feb 26, 2026
86.86Accuracy
5
Feb 26, 2026
73.17Accuracy
5
Feb 26, 2026
87.5Final Accuracy
4
Jun 24, 2026
0.191JSD
4
Jun 5, 2026
0.173JSD
4
Jun 5, 2026
0.181JSD
4
Jun 5, 2026
4.9Risk
4
May 21, 2026
1.29Wall-clock Time (hours)
4
May 12, 2026
22.52Latency (ms)
4
May 12, 2026
88.9NDCG@5
4
Apr 28, 2026