Summarization
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0Response-level Language Confusion
4
Jun 9, 2026
0Response-level Language Confusion
4
Jun 9, 2026
61.72FactKB Score
4
Jun 2, 2026
2.7Coherence
4
May 19, 2026
3.3Coherence
4
May 19, 2026
100Fidelity Rate (FR)
4
May 15, 2026
100FR
4
May 15, 2026
1.7Avg Accepted Draft Tokens per Round
4
May 12, 2026
1.5Acceptance Length (τ)
4
May 7, 2026
37.1ROUGE-1
4
Apr 29, 2026
0.428BLEURT Score
4
Apr 24, 2026
0.433BLEURT
4
Apr 24, 2026
14.3CNN Score
4
Apr 23, 2026
37.44R-1 Score
4
Apr 16, 2026
67.2Reward
4
Apr 1, 2026
83.3Pass Rate
4
Mar 20, 2026
37.29ROUGE-1
4
Feb 26, 2026
2.89Relevance
4
Feb 26, 2026
44.05ROUGE-1
4
Feb 26, 2026
22.46Average Score
4
Feb 26, 2026
50.5Winrate
4
Feb 26, 2026
0.837AUC-ROC
4
Feb 26, 2026
49WTR Llama2 Score
4
Feb 26, 2026
17.3ROUGE-2 (0-shot)
4
Feb 26, 2026
0.52Rank 1 Frequency
4
Feb 26, 2026