Last updated: April 5, 2026 | Reviewed by Daniel Ashford

The LLM Judge Index

Independent, multi-dimensional AI model evaluation by Daniel Ashford. 570+ models ranked. Methodology

Full Leaderboard - 570 Models

Data by Artificial Analysis | Updated hourly
#ModelIntelGPQACodeInput $/MLicense
1
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic
59.992.6%76.5$10.0Prop.2
GPT-5.6 Sol (max)OpenAI
58.994.1%77.4$5.0Prop.3
GPT-5.6 Sol (xhigh)OpenAI
57.793.1%78.3$5.0Prop.4
GPT-5.6 Sol (high)OpenAI
55.992.8%77.2$5.0Prop.5
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic
55.792%74.3$5.0Prop.6
GPT-5.6 Terra (max)OpenAI
55.092.5%76.7$2.5Prop.7
GPT-5.5 (xhigh)OpenAI
54.893.5%74.9$5.0Prop.8
Grok 4.5 (high)SpaceXAI
53.893.1%72.4$2.0Prop.9
GPT-5.6 Sol (medium)OpenAI
53.692.6%76.3$5.0Prop.10
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic
53.591.4%73.6$5.0Prop.11
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic
53.491.1%71.5$2.0Prop.12
GPT-5.5 (high)OpenAI
53.193.2%71.6$5.0Prop.13
GPT-5.6 Terra (xhigh)OpenAI
51.690.8%70.6$2.5Prop.14
GPT-5.4 (xhigh)OpenAI
51.492%71.1$2.5Prop.15
GPT-5.6 Luna (max)OpenAI
51.291.1%71.4$1.0Prop.16
GLM-5.2 (max)Z AI
51.189.5%68.8$1.4Prop.17
GPT-5.5 (medium)OpenAI
50.492.6%71.5$5.0Prop.18
Gemini 3.5 Flash (high)Google
50.292.2%70.1$1.5Prop.19
GPT-5.6 Sol (low)OpenAI
49.489.8%69.7$5.0Prop.20
GPT-5.6 Luna (xhigh)OpenAI
49.189.5%68.6$1.0Prop.21
GPT-5.6 Terra (high)OpenAI
49.089.6%67.1$2.5Prop.22
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic
47.287.5%63.0$3.0Prop.23
Gemini 3.1 Pro PreviewGoogle
46.594.1%68.8$2.0Prop.24
GPT-5.6 Luna (high)OpenAI
46.189.2%63.3$1.0Prop.25
Qwen3.7 MaxAlibaba
46.092.3%66.0$2.5Prop.26
GPT-5.6 Terra (medium)OpenAI
45.687.2%64.7$2.5Prop.27
Gemini 3.5 Flash (medium)Google
45.492.1%-$1.5Prop.28
MiniMax-M3MiniMax
44.492.9%58.6$0.30Prop.29
GPT-5.3 Codex (xhigh)OpenAI
44.391.5%-$1.8Prop.30
DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek
44.388.8%59.4$0.43Prop.31
Kimi K2.6Kimi
44.291.1%61.8$0.95Prop.32
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic
43.789.6%-$5.0Prop.33
GPT-5.5 (low)OpenAI
43.591%60.9$5.0Prop.34
Muse SparkMeta
43.188.4%58.6-Prop.35
Claude Opus 4.7 (Non-reasoning, High Effort)Anthropic
42.788.5%-$5.0Prop.36
MiMo-V2.5-ProXiaomi
42.286.6%60.2$0.43Prop.37
GPT-5.2 (xhigh)OpenAI
42.290.3%-$1.8Prop.38
Kimi K2.7 CodeKimi
41.989.6%60.8$0.95Prop.39
Claude Sonnet 5 (Non-reasoning, High Effort)Anthropic
41.780%66.4$2.0Prop.40
GPT-5.6 Sol (Non-reasoning)OpenAI
41.279%65.1$5.0Prop.41
Nex-N2-ProNex AGI
41.089.2%59.1$0.50Prop.42
DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek
40.890.5%-$0.43Prop.43
Claude Opus 4.5 (Reasoning)Anthropic
40.886.6%-$5.0Prop.44
GPT-5.6 Terra (low)OpenAI
40.584.3%58.1$2.5Prop.45
DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek
40.389.4%56.2$0.14Prop.46
MiMo-V2-ProXiaomi
40.387%-$1.0Prop.47
GLM-5.1 (Reasoning)Z AI
40.286.8%55.8$1.4Prop.48
MiMo-V2.5Xiaomi
40.184.9%-$0.14Prop.49
GPT-5.2 Codex (xhigh)OpenAI
40.189.9%-$1.8Prop.50
GPT-5.4 mini (xhigh)OpenAI
40.087.5%56.1$0.75Prop.
Showing top 50 of 570 models. Full data powered by Artificial Analysis.

Best LLM By Use Case

💻
Best for Code Generation
Weighted ranking
💬
Best for Customer Chatbot
Weighted ranking
✍️
Best for Content Writing
Weighted ranking
📊
Best for Data Analysis
Weighted ranking
🔬
Best for Research & RAG
Weighted ranking
🛡️
Best for Safety-Critical
Weighted ranking

Best LLM By Industry

🎓
Education
Schools, tutoring and edtech
🏥
Healthcare
Hospitals, clinics and health tech
🏦
Financial Services
Banking, investment and fintech
⚖️
Legal
Law firms, contracts and legal tech
💬
Customer Support
Help desks, chatbots and CX

Popular Comparisons

Claude Opus 4 vs GPT-5.3 Codex
Full comparison
Claude Opus 4 vs Gemini 2.5 Ultra
Full comparison
Claude Opus 4 vs Claude Sonnet 4
Full comparison
Claude Opus 4 vs GPT-4o
Full comparison
Claude Opus 4 vs Llama 4 405B
Full comparison
Claude Opus 4 vs Mistral Large 3
Full comparison
Claude Opus 4 vs Qwen 3.5 Plus
Full comparison
Claude Opus 4 vs DeepSeek V3
Full comparison

LLM Glossary

47 AI and language model terms explained. Browse all

Large Language Model (LLM)
An AI system trained on massive text data to understand and generate human language.
Tokens
The basic units of text that LLMs process — roughly 3/4 of a word.
Context Window
The maximum amount of text an LLM can process in a single request.
Hallucination
When an LLM generates plausible-sounding but factually incorrect information.
Inference
The process of an LLM generating a response to your input.
Prompt
The text input you send to an LLM to get a response.
Fine-Tuning
Customizing a pre-trained LLM on your specific data to improve performance for your use case.
RAG (Retrieval-Augmented Generation)
A technique that gives LLMs access to external documents to improve accuracy and reduce hallucination.

By Provider

Anthropic (3)OpenAI (3)Google (2)Meta (1)Mistral (1)Alibaba (1)DeepSeek (1)