Description-guided molecule generation on TOMG-Bench

Metric: wAcc (higher is better)

LeaderboardDataset

Loading chart...

Results

#	Model↕	wAcc▼	Extra Data	Paper	Date↕	Code
1	Claude-3.5	35.92	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
2	Gemini-1.5-pro	34.8	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
3	GPT-4-turbo	34.23	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
4	GPT-4o	32.29	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
5	Claude-3	30.47	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
6	Llama-3.1-8B (OpenMolIns-large)	27.22	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
7	Galactica-125M (OpenMolIns-xlarge)	25.73	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
8	Llama3-70B-Instruct (INT4)	23.93	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
9	Galactica-125M (OpenMolIns-large)	23.42	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
10	Galactica-125M (OpenMolIns-medium)	19.89	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
11	GPT-3.5-turbo	18.58	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
12	Galactica-125M (OpenMolIns-small)	15.18	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
13	Llama3.1-8B-Instruct	14.09	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
14	Llama3-8B-Instruct	13.75	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
15	chatglm-9B	13.137	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
16	Galactica-125M (OpenMolIns-light)	13.136	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
17	Llama3.2-1B (OpenMolIns-large)	8.1	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
18	yi-1.5-9B	7.32	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
19	Mistral-7B-Instruct-v0.2	4.81	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
20	BioT5-base	4.21	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
21	MolT5-large	2.89	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
22	Llama-3.1-1B-Instruct	1.99	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
23	MolT5-base	1.3	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
24	MolT5-small	1.299	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code
25	Qwen2-7B-Instruct	0.15	No	TOMG-Bench: Evaluating LLMs on Text-based Open M...	2024-12-19	Code