Leaderboard

value rankings

Updated weekly

Each leaderboard uses transparent weighted scoring, current model context, and supporting analysis to help teams interpret the results with confidence. Only full-profile entries appear in rankings; broader catalog records remain available elsewhere on the site when only source-backed metadata is currently available.

Full-profile entries

245

Models with complete enough metadata and scoring coverage to be meaningfully ranked in this category.

Ranking basis

value

Scores combine benchmark evidence, product metadata, and cost/context signals when those fields are published.

Catalog caveat

Tracked models without full scoring remain in the directory and provider pages, but are not relied on for analytical ranking claims.

Rank	Model	Provider	Score	Context
#1	Gemini 3.1 Flash	Google DeepMind	91	1,048,576
#2	Gemini 2.5 Flash	Google DeepMind	90	1,048,576
#3	Gemini 3.0 Flash	Google DeepMind	90	1,048,576
#4	Gemini 2.0 Flash	Google DeepMind	89	1,048,576
#5	GPT-5.3 Instant	OpenAI	89	1,000,000
#6	Gemini 2.5 Flash Live	Google DeepMind	88	1,048,576
#7	Gemini 2.5 Flash Native Audio Preview	Google DeepMind	88	1,048,576
#8	Gemini 2.5 Flash-Lite	Google DeepMind	88	1,048,576
#9	Claude Haiku 4.5	Anthropic	87	200,000
#10	Command R+ 2026	Cohere	87	128,000
#11	Gemini 2.5 Pro	Google DeepMind	87	1,048,576
#12	Gemini 3.1 Flash-Lite	Google DeepMind	87	1,048,576
#13	Gemini 3.1 Pro	Google DeepMind	87	1,048,576
#14	GPT-5 mini	OpenAI	87	1,000,000
#15	Llama 4 Maverick	Meta	87	1,048,576
#16	Claude 3.7 Sonnet	Anthropic	86	200,000
#17	Claude Sonnet 4.5	Anthropic	86	1,000,000
#18	Claude Sonnet 4.6	Anthropic	86	1,000,000
#19	Gemini 3.0 Pro	Google DeepMind	86	1,048,576
#20	GPT-4.1 mini	OpenAI	86	1,048,576
#21	GPT-4o-mini	OpenAI	86	128,000
#22	GPT-5.4	OpenAI	86	1,000,000
#23	Mistral Large 25	Mistral AI	86	128,000
#24	o4-mini	OpenAI	86	200,000
#25	warpgrep-v2	Morph	86	128,000
#26	Gemini 1.5 Flash	Google DeepMind	85	1,048,576
#27	Gemini 2.0 Flash-Lite	Google DeepMind	85	1,048,576
#28	Gemini 2.5 Pro TTS	Google DeepMind	85	1,048,576
#29	GPT-4.1	OpenAI	85	1,048,576
#30	GPT-5 nano	OpenAI	85	1,000,000
#31	GPT-5.2	OpenAI	85	1,000,000
#32	morph-v3-fast-apply	Morph	85	128,000
#33	Claude Haiku 3.5	Anthropic	84	200,000
#34	Claude Sonnet 4	Anthropic	84	1,000,000
#35	GPT-4o	OpenAI	84	128,000
#36	Nova Pro	Amazon Web Services	84	300,000
#37	Sonar	Perplexity	84	128,000
#38	flash-compact	Morph	83	200,000
#39	Gemini 1.5 Pro	Google DeepMind	83	2,097,152
#40	GPT-5	OpenAI	83	1,000,000
#41	GPT-5.3-Codex	OpenAI	83	1,000,000
#42	Nova Lite	Amazon Web Services	83	300,000
#43	Claude Haiku 3	Anthropic	82	200,000
#44	Gemini 1.5 Flash-8B	Google DeepMind	82	1,048,576
#45	Sonar Reasoning Pro	Perplexity	82	200,000
#46	Claude Haiku 3	Anthropic	81	200,000
#47	Nova Micro	Amazon Web Services	81	128,000
#48	Claude Opus 4.6	Anthropic	80	1,000,000
#49	Codestral	Mistral AI	80	256,000
#50	Codestral Embed	Mistral AI	80	32,768
#51	Mistral Embed	Mistral AI	80	32,768
#52	Mistral Moderation	Mistral AI	80	32,768
#53	o4-mini-deep-research	OpenAI	80	200,000
#54	Sonar Deep Research	Perplexity	80	200,000
#55	Voxtral Mini Transcribe	Mistral AI	80	131,072
#56	Claude Haiku 3.5	Anthropic	79	200,000
#57	Claude Haiku 4.5	Anthropic	79	200,000
#58	Doubao-Seed-1.6	ByteDance / Doubao	79	128,000
#59	Doubao-Seed-1.6-Flash	ByteDance / Doubao	79	128,000
#60	Doubao-Seed-2.0-Code	ByteDance / Doubao	79	128,000
#61	Doubao-Seed-Code	ByteDance / Doubao	79	128,000
#62	image-01	MiniMax	79	8,192
#63	image-01-live	MiniMax	79	8,192
#64	MiniMax-M1	MiniMax	79	204,800
#65	MiniMax-Speech-02	MiniMax	79	8,192
#66	MiniMax-Text-01	MiniMax	79	204,800
#67	MiniMax-VL-01	MiniMax	79	204,800
#68	music-2.0	MiniMax	79	8,192
#69	Devstral Medium 1.0	Mistral AI	78	128,000
#70	ERNIE 3.5 128K	Baidu / ERNIE	78	128,000
#71	ERNIE 4.0 Turbo 8K	Baidu / ERNIE	78	128,000
#72	ERNIE 4.5 Turbo 32K	Baidu / ERNIE	78	32,768
#73	ERNIE Functions 8K	Baidu / ERNIE	78	128,000
#74	ERNIE Speed 128K	Baidu / ERNIE	78	128,000
#75	Magistral Medium 1.2	Mistral AI	78	128,000
#76	Mistral Large 3	Mistral AI	78	128,000
#77	Mistral Medium 3.1	Mistral AI	78	128,000
#78	Mistral OCR 2505	Mistral AI	78	32,768
#79	Mistral Small 3.1	Mistral AI	78	128,000
#80	Mistral Small 3.2 Open	Mistral AI	78	128,000
#81	o1-mini	OpenAI	78	128,000
#82	Pixtral 12B	Mistral AI	78	131,072
#83	Pixtral Large	Mistral AI	78	131,072
#84	Sonar Pro	Perplexity	78	200,000
#85	Voxtral Mini Open	Mistral AI	78	131,072
#86	Voxtral Small Open	Mistral AI	78	131,072
#87	Claude Sonnet 3	Anthropic	77	200,000
#88	CogVideoX	Z.AI	77	128,000
#89	CogView 4	Z.AI	77	128,000
#90	GLM-4.5	Z.AI	77	128,000
#91	GLM-4.5V	Z.AI	77	128,000
#92	GLM-4.6	Z.AI	77	128,000
#93	GLM-4.6V	Z.AI	77	128,000
#94	GLM-4.7	Z.AI	77	128,000
#95	GLM-5	Z.AI	77	128,000
#96	GLM-Image	Z.AI	77	128,000
#97	GLM-OCR	Z.AI	77	128,000
#98	Hunyuan Code	Tencent / Hunyuan	77	128,000
#99	Hunyuan Lite	Tencent / Hunyuan	77	128,000
#100	Hunyuan Standard	Tencent / Hunyuan	77	128,000
#101	Hunyuan T1	Tencent / Hunyuan	77	256,000
#102	Hunyuan T1 Vision	Tencent / Hunyuan	77	128,000
#103	Hunyuan TurboS	Tencent / Hunyuan	77	128,000
#104	Hunyuan TurboS LongText 128K	Tencent / Hunyuan	77	128,000
#105	Kimi K2	Moonshot AI / Kimi	77	131,072
#106	Kimi K2 Thinking	Moonshot AI / Kimi	77	256,000
#107	Kimi K2 Turbo Preview	Moonshot AI / Kimi	77	256,000
#108	Kimi K2.5	Moonshot AI / Kimi	77	256,000
#109	Vidu Q1	Z.AI	77	128,000
#110	GPT-5.4 Pro	OpenAI	76	1,000,000
#111	GPT-5.2 Pro	OpenAI	75	1,000,000
#112	Llama 3.3 70B Instruct	Meta	75	128,000
#113	MiniMax-M2	MiniMax	75	204,800
#114	MiniMax-M2.1	MiniMax	75	204,800
#115	MiniMax-M2.1-highspeed	MiniMax	75	204,800
#116	MiniMax-M2.5	MiniMax	75	204,800
#117	MiniMax-M2.5-highspeed	MiniMax	75	204,800
#118	gpt-oss-120b	OpenAI	74	131,072
#119	Step-3.5-Flash	StepFun	73	131,072
#120	Claude Sonnet 3	Anthropic	72	200,000
#121	Claude Sonnet 4	Anthropic	72	1,000,000
#122	Command A	Cohere	72	256,000
#123	Command A Reasoning	Cohere	72	128,000
#124	Command A Translate	Cohere	72	128,000
#125	Command A Vision	Cohere	72	128,000
#126	Command R+	Cohere	72	128,000
#127	Command R7B	Cohere	72	128,000
#128	Embed 4	Cohere	72	128,000
#129	Grok 3	xAI	72	131,072
#130	Grok 3 Mini	xAI	72	131,072
#131	Grok 4	xAI	72	256,000
#132	Grok 4 Fast Reasoning	xAI	72	131,072
#133	grok-image	xAI	72	131,072
#134	Claude Opus 4.1	Anthropic	71	200,000
#135	DeepSeek-Coder-V2	DeepSeek	71	128,000
#136	DeepSeek-Math-V2	DeepSeek	71	128,000
#137	DeepSeek-OCR	DeepSeek	71	16,384
#138	DeepSeek-OCR-2	DeepSeek	71	16,384
#139	DeepSeek-R1	DeepSeek	71	128,000
#140	DeepSeek-R1-Distill-Llama-70B	DeepSeek	71	128,000
#141	DeepSeek-V2.5	DeepSeek	71	128,000
#142	DeepSeek-V3	DeepSeek	71	128,000
#143	DeepSeek-V3.1	DeepSeek	71	128,000
#144	DeepSeek-V3.1-Base	DeepSeek	71	128,000
#145	DeepSeek-V3.2	DeepSeek	71	128,000
#146	DeepSeek-V3.2-Exp	DeepSeek	71	128,000
#147	DeepSeek-VL2-Small	DeepSeek	71	16,384
#148	Devstral 2 Open	Mistral AI	71	128,000
#149	Devstral Small 2	Mistral AI	71	128,000
#150	gpt-audio	OpenAI	71	128,000
#151	gpt-realtime	OpenAI	71	128,000
#152	Jamba 3B	AI21 Labs	71	256,000
#153	Jamba Large	AI21 Labs	71	256,000
#154	Jamba Large 1.6	AI21 Labs	71	256,000
#155	Jamba Mini	AI21 Labs	71	256,000
#156	Jamba Mini 1.6	AI21 Labs	71	256,000
#157	Jamba Mini 1.7	AI21 Labs	71	256,000
#158	Janus-Pro-7B	DeepSeek	71	16,384
#159	Llama 4 Scout	Meta	71	10,485,760
#160	Magistral Small 1.2 Open	Mistral AI	71	128,000
#161	Ministral 3 14B Open	Mistral AI	71	128,000
#162	Ministral 3 3B Open	Mistral AI	71	128,000
#163	Ministral 3 8B Open	Mistral AI	71	128,000
#164	Mistral Large 3 Open	Mistral AI	71	128,000
#165	Mistral Nemo 12B	Mistral AI	71	128,000
#166	phi-1	Microsoft	71	4,096
#167	phi-1_5	Microsoft	71	4,096
#168	phi-2	Microsoft	71	4,096
#169	Phi-3-medium-4k-instruct	Microsoft	71	4,096
#170	Phi-3-mini-4k-instruct	Microsoft	71	4,096
#171	Phi-3-vision-128k-instruct	Microsoft	71	128,000
#172	Phi-3.5-mini-instruct	Microsoft	71	131,072
#173	Phi-3.5-MoE-instruct	Microsoft	71	131,072
#174	Phi-3.5-vision-instruct	Microsoft	71	131,072
#175	Phi-4	Microsoft	71	16,384
#176	Phi-4-mini-flash-reasoning	Microsoft	71	131,072
#177	Phi-4-mini-instruct	Microsoft	71	131,072
#178	Phi-4-multimodal-instruct	Microsoft	71	131,072
#179	Phi-4-reasoning	Microsoft	71	131,072
#180	Phi-4-reasoning-plus	Microsoft	71	131,072
#181	Phi-4-reasoning-vision-15B	Microsoft	71	131,072
#182	Phi-tiny-MoE-instruct	Microsoft	71	4,096
#183	Qwen2.5-1.5B-Instruct	Alibaba Qwen	71	131,072
#184	Qwen2.5-14B-Instruct	Alibaba Qwen	71	131,072
#185	Qwen2.5-32B-Instruct	Alibaba Qwen	71	131,072
#186	Qwen2.5-3B-Instruct	Alibaba Qwen	71	131,072
#187	Qwen2.5-72B-Instruct	Alibaba Qwen	71	131,072
#188	Qwen2.5-7B-Instruct	Alibaba Qwen	71	131,072
#189	Qwen2.5-Max	Alibaba Qwen	71	131,072
#190	Qwen2.5-VL-72B-Instruct	Alibaba Qwen	71	131,072
#191	Qwen2.5-VL-7B-Instruct	Alibaba Qwen	71	131,072
#192	Qwen3-Coder-Next	Alibaba Qwen	71	131,072
#193	Qwen3.5-0.8B	Alibaba Qwen	71	131,072
#194	Qwen3.5-122B-A10B	Alibaba Qwen	71	131,072
#195	Qwen3.5-27B	Alibaba Qwen	71	131,072
#196	Qwen3.5-2B	Alibaba Qwen	71	131,072
#197	Qwen3.5-35B-A3B	Alibaba Qwen	71	131,072
#198	Qwen3.5-397B-A17B	Alibaba Qwen	71	131,072
#199	Qwen3.5-4B	Alibaba Qwen	71	131,072
#200	Qwen3.5-9B	Alibaba Qwen	71	131,072
#201	Claude Opus 4	Anthropic	70	200,000
#202	Llama 3.1 405B Instruct	Meta	70	128,000
#203	Llama 3.1 70B Instruct	Meta	70	128,000
#204	gpt-audio-mini	OpenAI	67	128,000
#205	gpt-oss-20b	OpenAI	67	131,072
#206	gpt-realtime-mini	OpenAI	67	128,000
#207	LFM2-24B-A2B	Liquid AI	67	32,768
#208	pplx-embed-v1-4b	Perplexity	67	8,192
#209	Llama 3.1 8B Instruct	Meta	66	128,000
#210	o3	OpenAI	66	200,000
#211	pplx-embed-v1-0.6b	Perplexity	66	8,192
#212	chatgpt-image-latest	OpenAI	65	32,768
#213	GPT Image 1	OpenAI	65	32,768
#214	gpt-image-1-mini	OpenAI	65	32,768
#215	o3-deep-research	OpenAI	65	200,000
#216	Claude Opus 3	Anthropic	64	200,000
#217	Code Llama 70B Instruct	Meta	64	8,192
#218	Llama 3.2 90B Vision Instruct	Meta	64	128,000
#219	Meta Llama 3 70B Instruct	Meta	64	8,192
#220	Llama 3.2 1B Instruct	Meta	63	128,000
#221	Llama 3.2 3B Instruct	Meta	63	128,000
#222	MiMo-VL-7B	Xiaomi	63	131,072
#223	Step3-VL-10B	StepFun	63	131,072
#224	Code Llama 34B Instruct	Meta	62	8,192
#225	GPT-4o mini Transcribe	OpenAI	62	128,000
#226	GPT-4o mini TTS	OpenAI	62	128,000
#227	GPT-4o Transcribe	OpenAI	62	128,000
#228	Meta Llama 3 8B Instruct	Meta	62	8,192
#229	o1	OpenAI	62	200,000
#230	FLUX 1.1 Pro	Black Forest Labs	61	512
#231	LFM2-8B-A1B	Liquid AI	61	32,768
#232	Llama 3.2 11B Vision Instruct	Meta	61	128,000
#233	Llama Guard 4 12B	Meta	60	131,072
#234	MiMo-Audio-7B	Xiaomi	60	131,072
#235	FLUX 1 Pro	Black Forest Labs	59	512
#236	Step-Audio-R1.1	StepFun	59	131,072
#237	Claude Opus 3	Anthropic	58	200,000
#238	Claude Opus 4	Anthropic	58	200,000
#239	FLUX 1.1 Pro Ultra	Black Forest Labs	58	512
#240	Llama Guard 3 11B Vision	Meta	56	131,072
#241	LFM2.5-1.2B-Instruct	Liquid AI	55	131,072
#242	LFM2.5-1.2B-Thinking	Liquid AI	55	131,072
#243	LFM2-2.6B	Liquid AI	53	32,768
#244	Prompt Guard 86M	Meta	50	512
#245	NextStep-1.1	StepFun	38	512

Why #1: Gemini 3.1 Flash

Google's Gemini 3.1 Flash for fast, cost-efficient multimodal inference with strong quality.

This model clears the current full-profile threshold for leaderboard methodology.

Why #2: Gemini 2.5 Flash

Google's Gemini 2.5 Flash with 1M context for fast, cost-efficient multimodal inference.

This model clears the current full-profile threshold for leaderboard methodology.

Why #3: Gemini 3.0 Flash

Google's Gemini 3.0 Flash for fast multimodal inference. Released alongside Gemini 3.0 Pro.

This model clears the current full-profile threshold for leaderboard methodology.