AI Model Leaderboard — Skytells

Skytells

Rank	Model	Provider	Score	Benchmarks	Inference	Agentic	Programming	Value	Price
101	GPT-5.4 Mini gpt-5.4-mini texttext-to-textlanguage	OpenAI	48.4 Benchmarks	48.4	52.5	12.9	21.6	29.1	$0.75 in / $4.5 out
102	GPT-5.5 Instant gpt-5.5-instant multimodalvisionmulti-input reasoning	OpenAI	48.3 Benchmarks	48.3	61.1	0.0	0.0	15.7
103	DeepSeek-V3.2 (Thinking) deepseek-reasoner codeprogrammingtool use	DeepSeek	47.7 Benchmarks	47.7	0.0	12.0	42.5	0.0
104	Inkling-Small inkling-small multimodalvisionmulti-input reasoning	Thinking Machines Lab	47.5 Benchmarks	47.5	58.2	55.0	57.9	54.7	$0.3 in / $1.2 out
105	MiniMax M3.1 Flash minimax-m3.1-flash multimodalvisionmulti-input reasoning	MiniMax	47.5 Benchmarks	47.5	66.7	0.0	0.0	70.9
106	LongCat-Flash-Thinking longcat-flash-thinking codeprogrammingtool use	Meituan	47.3 Benchmarks	47.3	0.0	0.0	18.0	0.0
107	MiMo-V2.5 mimo-v2.5 multimodalvisionmulti-input reasoning	Xiaomi	47.2 Benchmarks	47.2	85.2	0.0	28.0	78.6	$0.168 in / $0.336 out
108	Nemotron 3.5 Bolt (74B A9B 24GB) nemotron-3.5-bolt-74b-a9b-24gb multimodalvisionmulti-input reasoning	NVIDIA	46.6 Benchmarks	46.6	0.0	18.6	30.7	0.0
109	DeepSeek-R1-0528 deepseek-r1-0528 codeprogrammingtool use	DeepSeek	46.5 Benchmarks	46.5	22.1	0.0	5.0	45.6	$0.5 in / $2.15 out
110	Step3-VL-10B step3-vl-10b multimodalvisionmulti-input reasoning	StepFun	46.0 Benchmarks	46.0	0.0	0.0	0.0	0.0	N/A
111	Qwen3 Max Thinking qwen3-max-thinking multimodalvisionmulti-input reasoning	Alibaba Cloud / Qwen Team	45.6 Benchmarks	45.6	30.9	11.2	51.5	25.0	$1.2 in / $6 out
112	Claude Opus 4.1 claude-opus-4-1-20250805 multimodalvisionmulti-input reasoning	Anthropic	45.1 Benchmarks	45.1	0.0	67.4	60.4	0.0
113	K-EXAONE-236B-A23B k-exaone-236b-a23b multimodalvisionmulti-input reasoning	LG AI Research	44.7 Benchmarks	44.7	0.0	0.0	0.0	0.0	N/A
114	o4-mini o4-mini multimodalvisionmulti-input reasoning	OpenAI	44.6 Benchmarks	44.6	0.0	35.3	27.7	0.0	N/A
115	Sarvam-30B sarvam-30b codeprogrammingtool use	Sarvam AI	44.3 Benchmarks	44.3	0.0	5.4	3.9	0.0	N/A
116	Nova 2 Pro nova-2-pro multimodalvisionmulti-input reasoning	Amazon	43.7 Benchmarks	43.7	0.0	57.2	48.6	0.0	N/A
117	GPT OSS 120B High gpt-oss-120b-high multimodalvisionmulti-input reasoning	OpenAI	43.5 Benchmarks	43.5	0.0	0.0	0.0	0.0
118	Nemotron 3 Super (120B A12B) nemotron-3-super-120b-a12b codeprogrammingtool use	NVIDIA	43.5 Benchmarks	43.5	41.8	7.2	22.2	81.9	$0.085 in / $0.4 out
119	GLM-4.6 glm-4.6 multimodalvisionmulti-input reasoning	Zhipu AI	42.9 Benchmarks	42.9	26.2	34.8	42.6	46.2	$0.5 in / $2 out
120	Gemini 2.0 Flash Thinking gemini-2.0-flash-thinking multimodalvisionmulti-input reasoning	Google	42.6 Benchmarks	42.6	0.0	0.0	0.0	0.0

101

GPT-5.4 Mini

OpenAI

48.4

$0.75 in / $4.5 out

102

GPT-5.5 Instant

OpenAI

48.3

$5 in / $30 out

103

DeepSeek-V3.2 (Thinking)

DeepSeek

47.7

N/A

104

Page 6 of 21 · 416 models

Previous Next