AI Model Leaderboards

Rankings across capability, popularity, adoption, economic footprint, speed, and value. Updated every 6 hours.

Use this page when you want the best models for a specific goal, not just the biggest names.

Active Only Include Non-Active

Capability

Pure technical ability across benchmarks, arenas, and agent tasks.

Popularity

Blended public attention plus real-world traction and trend persistence.

Adoption

Observed practical footprint across providers, routing, and sustained usage proxies.

Economic Footprint

Evidence-weighted economic presence combining adoption, monetization, and distribution.

Value

Capability relative to cost for practical buyers comparing utility per dollar.

Ranking signals refreshed7m agoJun 17, 2026pipeline sync

Start with a lens above, keep Active Only on for the cleanest public view, and open deeper tables only when you want the supporting details.

Structured benchmark-backed rows

Signal-backed rows without full normalized tables

Benchmark-expected rows still catching up

Benchmark badges show how directly comparable a row is. Structured means normalized benchmark rows, Provider-reported means official benchmark claims without a normalized table yet, Arena only means competitive signal without broad benchmark coverage, and Pending means the model is tracked but benchmark ingestion is still catching up.

All Models LLMs Image Gen Vision

52 models

#▲	Model	Category	Adoption	Popularity	Economic	Value	Cat. Rank	Agent	Downloads
1	Gemma 2 9B GoogleOpen	Large Language Models	81.4	60.3	49.4	—	#96	41.1	4.1M
3	CodeLlama 70B MetaOpen	Code	80.0	65.4	51.0	—	#8	33.2	410.0M
6	llama-3-70b-instruct MetaOpen	Large Language Models	80.0	72.3	51.0	—	#97	55.8	40.0M
9	llama-3.1-405b-instruct MetaOpen	Large Language Models	79.5	64.4	50.3	—	#103	30.0	15.0M
12	Gemma 3 27B GoogleOpen	Large Language Models	77.9	61.4	46.9	—	#83	23.7	560.0M
13	Gemma 4 31B IT GoogleOpen	Multimodal	77.8	57.9	45.8	78.8	#5	—	8.4M
16	Llama 3.3 70B MetaOpen	Large Language Models	77.7	67.1	48.0	—	#94	31.9	3.2M
19	Llama 4 Maverick MetaOpen	Large Language Models	76.1	71.7	45.9	—	#52	18.3	2100.0M
22	DeepSeek-V3 DeepSeekOpen	Large Language Models	75.4	74.4	47.7	—	#40	41.8	320.0M
23	Qwen2.5-72B AlibabaOpen	Large Language Models	75.1	66.8	47.8	—	#100	54.9	2.8M
24	DeepSeek-R1 DeepSeekOpen	Large Language Models	75.1	63.9	47.3	—	#56	56.0	4.5M
35	Qwen3-235B AlibabaOpen	Large Language Models	72.3	62.3	44.0	—	#53	55.1	180.0M
53	Claude Opus 4.7 Anthropic	Multimodal	69.9	47.2	65.8	33.4	#23	60.1	97K
54	Command R+ CohereOpen	Large Language Models	69.7	57.6	53.6	—	#161	—	189K
67	GPT-4 Turbo OpenAI	Large Language Models	68.0	65.8	67.8	22.9	#46	32.8	—
71	GPT-4o OpenAI	Multimodal	68.0	62.6	63.8	39.4	#15	38.4	—
84	deepseek-v3.1 DeepSeekOpen	Large Language Models	66.3	46.9	38.1	—	#158	34.6	488K
86	qwen3-235b-a22b-instruct-2507 QwenOpen	Large Language Models	65.9	47.5	37.0	—	#146	33.1	1.1M
98	Claude 3.5 Sonnet AnthropicArchived	Multimodal	70.9	55.1	69.7	37.3	#35	43.7	0
108	DeepSeek-V3.2 DeepSeekOpen	Large Language Models	64.2	50.9	34.6	—	#163	45.5	869K
113	o3 OpenAI	Large Language Models	64.0	59.4	57.0	43.8	#29	62.9	—
115	GPT-4.1 OpenAI	Large Language Models	64.0	61.7	57.0	43.4	#26	56.9	—
117	DeepSeek-V4-Pro DeepSeekOpen	Large Language Models	63.9	52.2	31.8	—	#124	64.3	2.8M
131	kimi-k2.6 Moonshot AIOpen	Multimodal	63.1	51.8	47.8	59.9	#1	68.0	26K
132	GPT-4.5 OpenAIArchived	Large Language Models	68.7	47.2	76.6	7.7	#51	34.5	0
161	GPT-5 OpenAI	Large Language Models	62.5	49.1	50.3	46.8	#59	62.0	—
175	grok-4 xAI	Large Language Models	62.1	41.8	43.1	—	#118	36.3	61K
199	GPT-5.1 OpenAI	Large Language Models	61.2	50.7	51.0	48.3	#15	58.9	—
202	Llama 4 Scout MetaOpen	Multimodal	61.1	55.3	46.8	78.4	#11	17.0	—
212	GPT-5.2 OpenAI	Large Language Models	60.9	54.1	50.6	44.9	#6	66.4	—
218	kimi-k2-thinking Moonshot AI	Large Language Models	60.7	46.9	46.2	57.0	#64	47.5	5K
233	R1 Distill Qwen 32B DeepSeekOpen	Large Language Models	60.0	58.7	48.1	62.2	#34	47.0	—
239	GPT-5.4 OpenAI	Large Language Models	59.7	50.8	48.8	40.3	#2	71.3	—
243	Phi 4 MicrosoftOpen	Large Language Models	59.6	63.0	49.7	84.9	#21	8.3	—
263	GPT-5.5 OpenAI	Large Language Models	59.0	51.3	54.3	32.8	#1	63.8	—
391	DeepSeek V3.2 Speciale DeepSeekOpen	Large Language Models	55.9	49.2	44.7	68.2	#11	52.8	—
426	Qwen3 Max QwenOpen	Large Language Models	55.3	50.3	45.1	50.8	#39	59.5	—
443	Command A CohereOpen	Large Language Models	54.9	55.7	54.3	40.8	#24	21.8	—
455	Grok 4.1 Fast xAI	Multimodal	54.6	36.6	49.1	67.3	#8	43.1	—
489	MiniMax M1 MiniMaxOpen	Large Language Models	53.6	42.6	38.8	60.9	#80	—	—
496	Qwen3 Max Thinking QwenOpen	Large Language Models	53.5	48.1	42.6	50.6	#36	51.6	—
525	QwQ 32B QwenOpen	Large Language Models	53.0	57.3	36.9	—	#61	57.6	—
533	Qwen3.6 Plus QwenOpen	Multimodal	52.8	47.3	38.2	62.4	#7	39.4	—
542	Kimi K2 Moonshot AI	Large Language Models	52.6	50.5	45.7	57.8	#35	35.3	—
562	Qwen3.7 Max QwenOpen	Large Language Models	52.1	47.0	40.5	46.1	#27	46.7	—
568	Qwen3.7 Plus QwenOpen	Multimodal	51.9	47.0	40.6	66.8	#4	43.7	—
570	MiniMax M2 MiniMaxOpen	Large Language Models	51.9	53.8	41.1	66.2	#20	45.8	—
611	MiniMax M2.1 MiniMax	Large Language Models	51.1	51.1	38.6	63.5	#14	41.8	—
638	MiniMax M2.5 MiniMaxOpen	Large Language Models	50.4	50.3	39.3	72.7	#19	49.6	—
652	MiniMax M2.7 MiniMax	Large Language Models	50.0	49.8	36.9	64.7	#16	41.3	—

Page 1 of 2