🎮 Lmgame Bench: Leaderboard 🎲

Comparative Analysis (Radar Chart)

💡 Click a legend entry to isolate that model. Double-click additional ones to add them for comparison.

⏰ Time Tracker

03/25/2025

🔄 Controls

All data analysis can be replicated by checking this Jupyter notebook

	Player	Organization	Super Mario Bros (planning only) Score	Sokoban Score	2048 Score	Candy Crush Score	Tetris (planning only) Score	Ace Attorney Score
gemini-2.5-flash-preview-04-17 (thinking)	anthropic	2126.3	5.33	105.7	147.3	13.7	16

	Player	Organization	Super Mario Bros (planning only) Score	Sokoban Score	2048 Score	Candy Crush Score	Tetris (planning only) Score	Ace Attorney Score
1	o3-2025-04-16	openai	3445	8	128	647	42	16
2	gpt-4.1-2025-04-14	openai	2126.3	0	105.7	182	13.7	2
3	gpt-4o-2024-11-20	openai	2047.3	0	106.7	147.3	14	0
4	o4-mini-2025-04-16	openai	1448	5.33	120.6	487.3	25.3	4
5	gemini-2.5-pro-preview-05-06 (thinking)	google	1498.3	4.33	117.3	416.3	23.3	7
6	claude-3-7-sonnet-20250219 (thinking)	anthropic	1418.7	2.33	113.3	484	16.3	7
7	gemini-2.5-flash-preview-04-17 (thinking)	google	1385	1.67	106.6	334.7	16.3	4
8	llama-4-maverick-17b-128e-instruct-fp8	meta	1468.7	0	106	128.7	10.3	0
9	claude-3-5-sonnet-20241022	anthropic	1267.7	0	108.2	106	14.7	2
10	Random (x30)	unknown	986.97	0	100.4	116.5	10.2	0
11	o1-2024-12-17	openai	855	2.33	128.9	159	35	16
12	deepseek-r1	deepseek	n/a	1.33	105.2	447.3	14.3	0
13	grok-3-mini-beta (thinking)	xai	n/a	5.67	118.6	254	21.3	0
14	o1-mini-2024-09-12	openai	n/a	1.33	114	48	11.7	0

Note: 'n/a' in the table indicates no data point for that model.