DeepYard

🧠AI Models

Explore the leading AI models from OpenAI, Anthropic, Google, Meta, and more. Compare benchmarks, pricing, context windows, and modality support across frontier and open source models.

11 tools listed

AI Model Rankings

Best all-around quality — 31 models

#ModelOverall ScoreLinks
1
C
Claude Opus 4.6
AnthropicFrontier
95/100
Docs
2
C
Claude Opus 4.5
AnthropicFrontier
94/100
PaperDocs
3
G
GPT-5.2
OpenAIFrontier
93/100
Docs
4
o
o3 Pro
OpenAIFrontier
92/100
Docs
5
G
GPT-5.1
OpenAIFrontier
91/100
Docs
6
C
Claude Sonnet 4.6
AnthropicFrontier
90/100
Docs
7
G
Grok 4
xAIFrontier
89/100
Docs
8
o
o3
OpenAIFrontier
87/100
Docs
9
D
DeepSeek R1 0528
DeepSeekOSS
87/100
PaperDocs
10
D
DeepSeek V3.2
DeepSeekOSS
86/100
PaperDocs
11
G
Gemini 3 Flash
Google DeepMindFrontier
86/100
Docs
12
C
Claude Sonnet 4.5
AnthropicFrontier
85/100
PaperDocs
13
G
GPT-5
OpenAIFrontier
85/100
Docs
14
D
DeepSeek R1
DeepSeekOSS
84/100
PaperDocs
15
Q
Qwen3 Coder
Alibaba CloudOSS
84/100
Docs
16
o
o4 Mini
OpenAIFrontier
83/100
Docs
17
Q
Qwen3 235B A22B
Alibaba CloudOSS
82/100
PaperDocs
18
Q
Qwen3 Max
Alibaba CloudOSS
81/100
Docs
19
G
GPT-4.1
OpenAIFrontier
80/100
Docs
20
G
Gemini 2.5 Flash
Google DeepMindFrontier
79/100
Docs
21
L
Llama 4 Maverick
MetaOSS
76/100
PaperDocs
22
o
o3 Mini
OpenAIFrontier
76/100
Docs
23
G
GPT-4o
OpenAIFrontier
72/100
PaperDocs
24
M
Mistral Large
Mistral AIFrontier
71/100
Docs
25
L
Llama 4 Scout
MetaOSS
68/100
PaperDocs
26
Q
Qwen3 32B
Alibaba CloudOSS
67/100
PaperDocs
27
G
GPT-4o-mini
OpenAIFrontier
60/100
Docs
28
G
GLM-5
ZAIOSS
–/100
29
K
Kimi K2.5
Moonshot AIFrontier
–/100
30
M
MiniMax M2.5
MiniMax AIFrontier
–/100
31
Q
Qwen3 TTS
QwenOSS
–/100

Rankings based on Chatbot Arena, Artificial Analysis, LMSYS, and official benchmarks. Pricing from OpenRouter API. Speed metrics are median values from Artificial Analysis. Last updated: Feb 2026.

Filter:Open SourceCommercialFreeFreemiumPaidClear filters
Sort:Most PopularTop RankedTrendingNewest
8
D

DeepSeek V3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational...

OSSpaid
DeepSeekFree (self-hosted) / $0.26/1M input tokens (API)
11
D

DeepSeek R1

Open-source reasoning model rivaling o1 at a fraction of the cost

OSSFree
DeepSeek70.0KFree (self-hosted) / $0.40/1M input tokens (API)
12
L

Llama 4 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language mode...

OSSpaid
MetaFree (self-hosted) / $0.15/1M input tokens (API)
15
G

GLM-5

Open-source MoE model for bilingual English-Chinese text generation with commercial-friendly MIT license

OSSFree
ZAIFree (self-hosted)
20
Q

Qwen3 Coder

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation mod...

OSSpaid
Alibaba CloudFree (self-hosted) / $0.22/1M input tokens (API)
21
Q

Qwen3 TTS

Open-source TTS model with 12Hz audio generation and voice cloning capabilities

OSSFree
QwenFree (self-hosted)
23
Q

Qwen3 Max

Qwen3-Max is an updated release built on the Qwen3 series, offering major improv...

OSSpaid
Alibaba CloudFree (self-hosted) / $1.20/1M input tokens (API)
24
D

DeepSeek R1 0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance...

OSSpaid
DeepSeekFree (self-hosted) / $0.40/1M input tokens (API)
25
Q

Qwen3 235B A22B

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by ...

OSSpaid
Alibaba CloudFree (self-hosted) / $0.45/1M input tokens (API)
28
L

Llama 4 Scout

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model de...

OSSpaid
MetaFree (self-hosted) / $0.08/1M input tokens (API)
30
Q

Qwen3 32B

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series...

OSSpaid
Alibaba CloudFree (self-hosted) / $0.08/1M input tokens (API)