Polarization Detection on SemEval Task 9 2026 (test) benchmark leaderboard · SOTA2 Research

Polarization Detection on SemEval Task 9 2026 (test)

88.92Macro-F1language-adaptive modeling framework

Evaluation Results

Method
language-adaptive modeling framework2026.04	88.92	90.53	-0.0161	7
language-adaptive modeling framework2026.04	88.74	89.13	-0.0039	2
language-adaptive modeling framework2026.04	84.46	86.25	-0.0179	7
language-adaptive modeling framework2026.04	83.08	83.48	-0.004	3
language-adaptive modeling framework2026.04	82.94	84.88	-0.0194	12
language-adaptive modeling framework2026.04	81.68	83.36	-0.0168	6
Best of Sub 1 + Sub 42026.05	81.2	—	—	—
Ensemble + threshold2026.05	81.1	—	—	—
language-adaptive modeling framework2026.04	80.61	84.31	-0.037	13
language-adaptive modeling framework2026.04	80.32	82.36	-0.0204	17
Best Gemma-12B per lang2026.05	79.7	—	—	—
language-adaptive modeling framework2026.04	79.58	82.52	-0.0294	18
language-adaptive modeling framework2026.04	79.03	82.55	-0.0352	14
language-adaptive modeling framework2026.04	78.23	81.13	-0.029	15
language-adaptive modeling framework2026.04	77.44	80.02	-0.0258	10
language-adaptive modeling framework2026.04	76.32	80.3	-0.0398	22
Hybrid (XLM-R, Qwen3)2026.05	66.5	—	—	—