Text Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
188.12Throughput (tokens/s)
10
May 4, 2026
187.43Throughput (tokens/s)
10
Jun 2, 2026
4Diversity
10
Apr 21, 2026
35.5ROUGE-L
10
Mar 18, 2026
22.11F1 Score
10
Mar 16, 2026
26.5F1 Score
10
Mar 16, 2026
25.76F1 Score
10
Mar 16, 2026
5.03LCTG Error Rate
10
Feb 26, 2026
2.8LCTG Error Rate
10
Feb 26, 2026
2.58LCTG Error Rate
10
Feb 26, 2026
3.18LCTG Error Rate (E)
10
Feb 26, 2026
0.224BLEU-1
10
Feb 26, 2026
78.3Grammaticality
10
Feb 26, 2026
0.447Grammaticality
10
Feb 26, 2026
1.04Loss
9
Jun 30, 2026
67.47TPS
9
Jun 11, 2026
69.2BLEU Score
9
May 18, 2026
100ASR-G Sim (mean) @-1
9
Apr 1, 2026
53.7ROUGE-1
9
Feb 26, 2026
48.7ROUGE-1
9
Feb 26, 2026
21.1ROUGE-1
9
Feb 26, 2026
44.83Ratio
8
Jun 23, 2026
2NFE
8
Jun 11, 2026
5.91VIC Score
8
Jun 4, 2026
8.94Latency (ms/tok)
8
Jun 2, 2026