AI Model Leaderboard

Name: AllBenched AI model leaderboard
Creator: AllBenched

Reasoning ranking, Model families, sorted by Overall
Rank	Model	Provider	Weights	Overall	Coding	Agents	Reasoning	Math	Knowledge	Cost
79	Qwen3.8 27B	Alibaba	Open	55.2	57.7	56.3	57.0	54.4	52.6	$0.83
103	Qwen3.5 397B-A17B	Alibaba	Open	52.1	–No results	51.7	51.9	52.3	–No results	$1.35
117	Qwen3.6 27B	Alibaba	Open	50.0	48.1	–No results	47.5	53.1	–No results	$1.03
118	Qwen3.6 35B-A3B	Alibaba	Open	49.8	44.1	45.1	49.8	49.9	–No results	$0.36
130	Qwen3.5 35B-A3B	Alibaba	Open	48.4	39.1	–No results	48.2	48.7	–No results	$0.36
131	Qwen3 235B-A22B Thinking 2507	Alibaba	Open	48.1	47.5	30.6	45.8	48.0	53.4	$0.95
144	Qwen3.5 9B	Alibaba	Open	46.7	35.7	38.1	46.5	46.9	–No results	$0.14
153	Qwen3-30B-A3B-Thinking (Jul 2025)	Alibaba	Open	46.1	39.4	–No results	44.1	48.6	–No results	–No price
158	Qwen3 32B	Alibaba	Open	44.9	39.8	42.9	42.5	48.0	–No results	$0.26
159	Qwen3-14B	Alibaba	Open	44.8	37.9	39.7	42.3	47.9	–No results	–No price
167	Qwen3 8B	Alibaba	Open	42.9	27.6	40.3	40.4	46.1	–No results	$0.098
171	Qwen3 235B-A22B	Alibaba	Open	42.6	45.0	–No results	44.4	38.9	45.0	$0.50
197	Qwen2.5-VL 72B Instruct	Alibaba	Open	37.1	–No results	34.2	37.2	37.0	–No results	$1.01
207	Qwen2.5-32B	Alibaba	Open	36.0	–No results	–No results	36.0	36.0	–No results	–No price