Sentiment Analysis on SloESG-News 1.0 (test) benchmark leaderboard · SOTA2 Research

Sentiment Analysis on SloESG-News 1.0 (test)

68.79Accuracytabpfn_bge-m3_svd

Evaluation Results

Method	Links
tabpfn_bge-m3_svd2026.04		68.79	52.1	54.41	53.86
hf_sloberta2026.04		60.91	54.2	54.86	55.28
tabpfn_gemma-embed_svd2026.04		60.3	39.09	42.48	48.67
GaMS-9B2026.04		60	44.52	45.91	37.3
tabpfn_bge-m32026.04		58.79	44.57	45.71	51.64
tabpfn_paraphrase2026.04		58.18	42.39	43.37	47.39
tabpfn_paraphrase_svd2026.04		57.88	41.19	43.49	45.6
tabpfn_gemma-embed2026.04		56.36	38.67	39.74	47.51
gpt-oss 20B2026.04		53.64	47.92	48.21	38.39
hf_xlm-roberta2026.04		53.33	35.9	38.43	48.49
FinalTowerA2026.04		51.52	37.42	39.97	43.51
GaMS-27B2026.04		50	38.99	44.05	36.2
FinalTowerB2026.04		49.39	39.35	41.58	43.42
Majority2026.04		48.18	16.26	25	25
Gemma3-12B2026.04		47.27	48.7	51.2	42.94
Gemma3-27B2026.04		40.91	41.46	45.29	38.16
gpt-oss 20B2026.04		0.5273	0.4512	0.4547	0.3603
GaMS-9B2026.04		0.5182	0.4193	0.4432	0.3529
GaMS-27B2026.04		0.5	0.414	0.4358	0.3395
hf_xlm-roberta2026.04		0.4939	0.4404	0.4423	0.4533
hf_sloberta2026.04		0.4909	0.4238	0.4265	0.4475
tabpfn_gemma-embed_svd2026.04		0.4727	0.294	0.36	0.3962
FinalTowerA2026.04		0.4606	0.3033	0.3589	0.3515
tabpfn_paraphrase_svd2026.04		0.4545	0.2804	0.3443	0.3987
tabpfn_gemma-embed2026.04		0.4515	0.3177	0.3529	0.4083
tabpfn_bge-m3_svd2026.04		0.4515	0.2804	0.3418	0.3821
tabpfn_bge-m32026.04		0.4455	0.2726	0.336	0.4051
Gemma3-27B2026.04		0.4455	0.4022	0.4622	0.343
tabpfn_paraphrase2026.04		0.4424	0.2674	0.3336	0.4072
FinalTowerB2026.04		0.4364	0.3252	0.3602	0.3557
Gemma3-12B2026.04		0.4182	0.3717	0.4179	0.3369
Majority2026.04		0.3364	0.1259	0.25	0.25