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 refreshedjust nowSep 16, 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

Tracked Non-Active Models

Preview, beta, deprecated, and archived models stay visible here without changing the default public leaderboard.

Include Them

Show tracked non-active models

Model	Status	Popularity
Gemma 2 9B Google	Archived	#8
Gemma 3 27B Google	Archived

70 models

#▲	Model	Category	Economic Footprint	Popularity	Adoption	Value	Cat. Rank	Agent	Downloads
1	GPT-5.6 Sol OpenAI	Large Language Models	74.7	51.1	84.4	40.0	#2	56.6	88K
2	Claude Fable 5.1 Anthropic	Multimodal	67.2	40.6	63.9	26.8	#47	71.5	0
3	Claude Sonnet 5 Anthropic	Multimodal	66.9	48.0	80.4	47.2	#7	49.8	121K
4	GPT-5.2 Pro OpenAI	Large Language Models	66.9	48.7	62.0	17.7	#18	58.1	—
5	o3 Pro OpenAI	Multimodal	66.9	45.5	64.4	16.0	#43	57.8	—
6	Llama 3.1 8B Instruct MetaOpen	Large Language Models	63.9	60.2	85.0	97.4	#22	26.1	5.7M
9	Claude Fable 5 Anthropic	Multimodal	63.3	42.2	68.9	27.0	#55	65.2	31K
11	GPT-5.4 Pro OpenAI	Large Language Models	62.0	41.1	60.9	12.3	#7	61.7	—
13	Llama 3.3 70B Instruct MetaOpen	Large Language Models	61.6	55.1	82.3	87.7	#87	22.0	928K
16	GPT-4o OpenAI	Multimodal	60.6	50.0	68.0	39.2	#62	36.0	—
17	Gemma 3 GoogleOpen	Large Language Models	60.2	52.4	82.0	97.8	#89	—	650K
21	Qwen3 235B A22B QwenOpen	Large Language Models	58.5	51.2	75.6	69.3	#112	52.5	352K
30	GPT-5.6 Terra OpenAI	Large Language Models	56.6	50.4	73.8	49.1	#72	58.6	56K
34	o3 OpenAI	Large Language Models	55.8	46.5	65.2	44.1	#91	57.8	—
35	GPT-4.1 OpenAI	Large Language Models	55.8	46.5	65.2	43.5	#66	55.0	—
36	GPT-5.4 Image 2 OpenAI	Image Generation	55.8	40.3	60.2	26.1	#1	70.6	—
39	Claude 4 Sonnet Anthropic	Multimodal	55.0	56.6	60.2	37.3	#44	56.7	0
50	GPT-5.2 OpenAI	Large Language Models	53.7	54.0	62.1	48.5	#4	62.3	—
53	GPT-5.4 OpenAI	Large Language Models	53.5	52.3	60.9	43.8	#3	70.6	—
54	Kimi K3 Moonshot AIOpen	Multimodal	53.5	54.0	69.1	44.9	#48	36.2	2.2M
57	Qwen3.8 2.4T A95B QwenOpen	Large Language Models	53.0	43.0	66.7	47.0	#94	50.5	52K
60	GPT-5.1 OpenAI	Large Language Models	52.8	49.2	62.4	52.2	#48	55.9	—
62	Kimi K2.6 Moonshot AIOpen	Multimodal	52.4	50.5	68.4	60.2	#53	64.6	539K
65	Claude Opus 5 Anthropic	Multimodal	52.3	44.6	54.5	35.2	#9	70.1	0
71	Gemma 4 26B A4B IT GoogleOpen	Multimodal	51.5	51.2	79.0	91.4	#46	—	9.2M
82	Kimi K2 Thinking Moonshot AI	Large Language Models	50.2	44.8	67.4	60.3	#150	50.5	51K
87	Kimi K2.7 Code Moonshot AI	Multimodal	49.8	46.3	66.1	63.8	#65	47.9	170K
88	Llama 3.2 3B Instruct MetaOpen	Large Language Models	49.7	56.3	84.1	93.9	#160	—	1.8M
93	Qwen3.8 27B QwenOpen	Multimodal	49.5	55.0	72.2	80.8	#2	59.2	7.7M
95	Qwen2.5-72B AlibabaOpen	Large Language Models	49.4	57.3	76.3	—	#131	52.0	2.8M
96	GPT-5.6 Luna OpenAI	Large Language Models	49.2	53.7	75.3	80.2	#67	46.4	173K
97	qwen3-7-plus QwenOpen	Multimodal	49.1	43.6	68.8	72.4	#51	40.0	150K
99	DeepSeek-R1 DeepSeekOpen	Large Language Models	48.8	58.6	76.3	—	#110	55.4	4.5M
102	DeepSeek-V3 DeepSeekOpen	Large Language Models	48.7	65.7	75.2	—	#118	39.0	1.0M
106	Mistral Large 3 Mistral AIOpen	Multimodal	48.5	37.4	55.0	60.2	#27	31.8	—
110	gpt-oss-120b OpenAIOpen	Large Language Models	48.2	56.2	83.7	96.8	#105	6.1	5.3M
117	Gemini 3 Pro Image Google	Image Generation	47.6	38.6	58.2	43.5	#2	56.0	—
120	Llama 4 Maverick MetaOpen	Large Language Models	47.5	63.1	77.3	—	#111	19.4	2100.0M
122	Nemotron 70B NVIDIAOpen	Large Language Models	47.3	57.6	71.9	—	#241	53.5	620K
132	Grok 4.3 xAI	Large Language Models	46.6	38.2	53.6	53.7	#85	46.7	—
159	grok-4 xAI	Large Language Models	44.7	42.7	63.3	—	#207	46.7	61K
163	QwQ 32B QwenOpen	Large Language Models	44.5	52.1	69.1	—	#405	51.4	69K
164	Qwen3-235B AlibabaOpen	Large Language Models	44.4	53.5	70.5	—	#122	55.3	340K
169	Grok 4.6 xAI	Multimodal	44.1	34.0	52.2	45.4	#4	46.7	0
196	GPT-5.6 Sol Pro OpenAI	Large Language Models	41.8	45.4	59.2	42.5	#12	46.4	—
198	GPT-5.6 Terra Pro OpenAI	Large Language Models	41.8	45.4	59.2	42.5	#13	46.4	—
205	Qwen3 Max Thinking QwenOpen	Large Language Models	41.0	36.7	54.7	48.2	#49	48.6	—
222	Qwen3.7 Max QwenOpen	Large Language Models	39.5	35.1	53.3	41.5	#38	42.3	—
229	Qwen3.5 Plus 2026-02-15 QwenOpen	Multimodal	38.9	36.6	54.6	63.5	#35	40.6	—
230	Qwen3.8 Max (0902) QwenOpen	Multimodal	38.9	34.0	51.9	38.8	#26	44.8	0

Page 1 of 2