AI Model Leaderboard

Name: AllBenched AI model leaderboard
Creator: AllBenched

Balanced ranking, Model families, sorted by Overall
Rank	Model	Provider	Overall	Coding	Agents	Reasoning	Math	Knowledge	Cost
211	Grok-2 (Dec 2024)	xAI	36.5	35.0	–No results	38.2	37.0	37.5	–No price
191	X-Ai/Grok-4-Fast-Non-Reasoning	xAI	40.2	38.0	–No results	42.1	–No results	31.8	$0.28
171	Grok 4.1 Fast	xAI	43.3	36.6	48.0	47.0	50.4	37.2	$0.28
168	x-AI/Grok-Code-Fast 1	xAI	43.6	44.3	45.5	45.1	–No results	–No results	$0.53
167	Grok 3	xAI	43.8	42.9	45.3	43.5	44.5	43.2	–No price
166	Grok-3 mini	xAI	43.9	42.1	–No results	45.2	47.3	–No results	–No price
136	X-Ai/Grok-4-Fast-Reasoning	xAI	47.0	48.9	–No results	51.9	–No results	42.9	$0.28
110	Grok 4.1 Fast (Reasoning)	xAI	50.3	48.8	52.2	56.5	50.4	49.6	$0.28
105	Grok 4	xAI	50.7	51.8	48.7	54.9	51.2	51.5	–No price
95	Grok 4.3	xAI	52.6	54.2	50.3	56.0	54.9	50.4	$1.56
87	Grok 4.20 (Reasoning)	xAI	53.4	54.2	52.5	60.1	55.2	49.9	$1.56
57	Grok 4.5	xAI	57.5	58.9	58.7	59.9	57.5	58.0	$3.00
32	Grok 4.6	xAI	59.8	60.9	60.4	61.6	59.2	59.4	$3.00
28	Grok 4.7	xAI	60.1	61.2	60.8	60.7	56.8	59.3	$3.00