AI Model Leaderboard — Skytells

Skytells

Rank	Model	Provider	Score	Benchmarks	Inference	Agentic	Programming	Value	Price
101	Qwen3-Next-80B-A3B-Thinking qwen3-next-80b-a3b-thinking textinference	Alibaba Cloud / Qwen Team	42.0 overall	42.3	0.0	41.7	0.0	0.0	N/A
102	Qwen3 VL 235B A22B Instruct qwen3-vl-235b-a22b-instruct multimodalvisionmulti-input reasoning	Alibaba Cloud / Qwen Team	42.0 overall	34.3	0.0	51.0	0.0	0.0
103	Qwen3-Coder 480B A35B Instruct qwen3-coder-480b-a35b-instruct codeprogrammingtool use	Alibaba Cloud / Qwen Team	41.8 overall	0.0	0.0	50.7	32.1	0.0
104	Qwen3.5-35B-A3B qwen3.5-35b-a3b multimodalvisionmulti-input reasoning	Alibaba Cloud / Qwen Team	41.6 overall	53.4	0.0	38.3	30.2	0.0	N/A
105	GLM-4.6 glm-4.6 multimodalvisionmulti-input reasoning	Zhipu AI	41.2 overall	44.5	0.0	35.4	43.2	0.0	N/A
106	Kimi K2 0905 kimi-k2-0905 textinference	Moonshot AI	41.0 overall	41.0	0.0	0.0	0.0	0.0	N/A
107	Qwen3-235B-A22B-Instruct-2507 qwen3-235b-a22b-instruct-2507 textinference	Alibaba Cloud / Qwen Team	40.7 overall	40.7	0.0	0.0	0.0	0.0	N/A
108	LongCat-Flash-Lite longcat-flash-lite codeprogrammingtool use	Meituan	40.1 overall	22.8	72.8	30.1	23.9	95.6	$0.1 in / $0.4 out
109	Gemini 2.5 Pro Preview 06-05 gemini-2.5-pro-preview-06-05 multimodalvisionmulti-input reasoning	Google	39.4 overall	50.2	0.0	0.0	25.8	0.0
110	DeepSeek-V3.2-Exp deepseek-v3.2-exp codeprogrammingtool use	DeepSeek	39.1 overall	50.2	0.0	27.2	38.0	0.0	N/A
111	LongCat-Flash-Thinking-2601 longcat-flash-thinking-2601 codeprogrammingtool use	Meituan	38.3 overall	52.9	0.0	25.6	33.5	0.0
112	Mistral Small 4 mistral-small-latest multimodalvisionmulti-input reasoning	Mistral AI	38.2 overall	31.3	23.2	0.0	0.0	81.7
113	Grok Code Fast 1 grok-code-fast-1 codeprogrammingtool use	xAI	38.2 overall	0.0	27.2	0.0	36.1	60.5	$0.2 in / $1.5 out
114	o4-mini o4-mini multimodalvisionmulti-input reasoning	OpenAI	37.7 overall	46.2	0.0	36.1	28.7	0.0	N/A
115	QvQ-72B-Preview qvq-72b-preview multimodalvisionmulti-input reasoning	Alibaba Cloud / Qwen Team	37.6 overall	37.6	0.0	0.0	0.0	0.0	N/A
116	Gemini 3.5 Flash-Lite gemini-3.5-flash-lite multimodalvisionmulti-input reasoning	Google	37.6 overall	18.9	84.8	0.0	17.2	59.1
117	MiMo-V2-Flash mimo-v2-flash codeprogrammingtool use	Xiaomi	37.4 overall	50.6	0.0	23.5	35.8	0.0	N/A
118	DeepSeek-V3.2 deepseek-v3.2 codeprogrammingtool use	DeepSeek	37.3 overall	55.0	0.0	12.4	42.0	0.0	N/A
119	GLM-5 glm-5 codeprogrammingtool use	Zhipu AI	37.3 overall	0.0	6.9	35.1	60.4	40.0	$1 in / $3.2 out
120	DeepSeek R1 Zero deepseek-r1-zero textinference	DeepSeek	36.8 overall	36.8	0.0	0.0	0.0	0.0	N/A