ganda-gemma-1b/luganda_results.csv

1	Rank	Model	Type	BLEU	chrF++	Our Model
2	1	Google Translate	Commercial Service	9.27	46.44	FALSE
3	2	Claude Sonnet 4	Anthropic	8.07	43.54	FALSE
4	3	Gemini 2.0 Flash 001	Google	7.94	43.38	FALSE
5	4	Gemini 2.5 Pro	Google	7.46	44.74	FALSE
6	5	Ganda Gemma 1B (Our Model)	Specialized Fine-tuned	6.99	40.32	TRUE
7	6	Gemini 2.5 Flash	Google	6.28	40.51	FALSE
8	7	Chatgpt 4o Latest	OpenAI	6.19	40	FALSE
9	8	Gpt Oss 120B	OpenAI	5.16	34.7	FALSE
10	9	Gpt 5 Mini	OpenAI	5.14	36.55	FALSE
11	10	Gpt 5 Nano	OpenAI	4.93	32.86	FALSE
12	11	Llama 4 Maverick	Meta	4.52	33.75	FALSE
13	12	Gemma 3 27B	Google	3.65	31.37	FALSE
14	13	Llama 4 Scout	Meta	3.59	27.63	FALSE
15	14	Gpt Oss 20B	OpenAI	3.39	27.98	FALSE
16	15	Gemma 3 4B	Google	1.1	20.05	FALSE
17	16	Gemma 3N E4B	Google	0.84	17.6	FALSE
18	17	Gemma 3 1B (vLLM Baseline)	General Model	0.51	9.79	FALSE