AI Model Leaderboard — Skytells

Skytells

Rank	Model	Provider	Score	Benchmarks	Inference	Agentic	Programming	Value	Price
41	Step-3.5-Flash step-3.5-flash codeprogrammingtool use	StepFun	42.0 Agentic	62.8	60.4	42.0	50.6	95.0	$0.1 in / $0.4 out
42	Qwen3.5-35B-A3B qwen3.5-35b-a3b multimodalvisionmulti-input reasoning	Alibaba Cloud / Qwen Team	41.8 Agentic	55.9	41.1	41.8	31.6	56.3	$0.25 in / $2 out
43	Qwen3-Next-80B-A3B-Thinking qwen3-next-80b-a3b-thinking textinference	Alibaba Cloud / Qwen Team	41.7 Agentic	43.4	0.0	41.7	0.0	0.0	N/A
44	Claude Opus 4.5 claude-opus-4-5-20251101 multimodalvisionmulti-input reasoning	Anthropic	41.4 Agentic	55.3	0.0	41.4	73.5	0.0
45	MiniMax M2 minimax-m2 codeprogrammingtool use	MiniMax	41.2 Agentic	30.6	41.8	41.2	41.5	59.5	$0.3 in / $1.2 out
46	MiniMax M2.7 minimax-m2.7 codeprogrammingtool use	MiniMax	40.1 Agentic	0.0	25.3	40.1	39.6	67.7	$0.3 in / $1.2 out
47	Qwen3 VL 235B A22B Thinking qwen3-vl-235b-a22b-thinking multimodalvisionmulti-input reasoning	Alibaba Cloud / Qwen Team	39.3 Agentic	36.8	0.0	39.3	0.0	0.0
48	Gemini 3 Flash gemini-3-flash-preview multimodalvisionmulti-input reasoning	Google	38.8 Agentic	70.0	72.2	38.8	63.7	44.9
49	Claude 3.5 Sonnet claude-3-5-sonnet-20241022 multimodalvisionmulti-input reasoning	Anthropic	38.7 Agentic	33.0	0.0	38.7	11.9	0.0
50	MiniMax M3 minimax-m3 multimodalvisionmulti-input reasoning	MiniMax	38.7 Agentic	54.6	72.2	38.7	74.3	48.1	$0.6 in / $2.4 out
51	o4-mini o4-mini multimodalvisionmulti-input reasoning	OpenAI	37.5 Agentic	47.6	0.0	37.5	30.1	0.0	N/A
52	GLM-4.5 glm-4.5 codeprogrammingtool use	Zhipu AI	36.2 Agentic	32.6	0.0	36.2	38.0	0.0	N/A
53	GLM-4.6 glm-4.6 multimodalvisionmulti-input reasoning	Zhipu AI	36.0 Agentic	45.6	0.0	36.0	43.9	0.0	N/A
54	GPT-4.5 gpt-4.5 multimodalvisionmulti-input reasoning	OpenAI	35.8 Agentic	41.3	0.0	35.8	5.5	0.0	N/A
55	Qwen3 VL 32B Thinking qwen3-vl-32b-thinking multimodalvisionmulti-input reasoning	Alibaba Cloud / Qwen Team	34.1 Agentic	43.3	0.0	34.1	0.0	0.0
56	GPT-4.1 gpt-4.1-2025-04-14 multimodalvisionmulti-input reasoning	OpenAI	32.8 Agentic	27.9	76.0	32.8	15.8	36.7
57	Qwen3.5-397B-A17B qwen3.5-397b-a17b multimodalvisionmulti-input reasoning	Alibaba Cloud / Qwen Team	31.1 Agentic	57.0	41.1	31.1	57.7	39.2	$0.6 in / $3.6 out
58	LongCat-Flash-Lite longcat-flash-lite codeprogrammingtool use	Meituan	30.1 Agentic	23.6	74.7	30.1	24.5	96.5	$0.1 in / $0.4 out
59	LongCat-Flash-Thinking-2601 longcat-flash-thinking-2601 codeprogrammingtool use	Meituan	29.0 Agentic	54.9	0.0	29.0	35.2	0.0
60	DeepSeek-V3.2-Exp deepseek-v3.2-exp codeprogrammingtool use	DeepSeek	28.0 Agentic	51.5	0.0	28.0	38.8	0.0	N/A