Aggregated AI Model Rankings
Rankings across independent sources, with each source position shown separately. Published 16 categories from 8 independent sources.
Updated 2026-09-20. Rank method: Medal count: most 1st places, then 2nds, then 3rds … through 10ths; ties by more boards present, then name
Overall / Chat
- Claude Fable 5.1 by Anthropic, category rank #1; source ranks: OpenRouter #10, Arena.ai #5, Artificial Analysis #1, LLM Stats #2, Design Arena #6, Vellum #1, Vals.ai #1, LiveBench #1
- GPT-6 Astra by OpenAI, category rank #2; source ranks: OpenRouter #2, Artificial Analysis #2, LLM Stats #1, Design Arena #3, Vals.ai #3, LiveBench #3
- Claude Opus 5 by Anthropic, category rank #3; source ranks: OpenRouter #1, Arena.ai #10, Artificial Analysis #3, LLM Stats #5, Design Arena #8, Vellum #3, Vals.ai #2, LiveBench #8
- Claude Fable 5 by Anthropic, category rank #4; source ranks: OpenRouter #8, Arena.ai #1, LLM Stats #7, Vals.ai #4, LiveBench #2
- Kimi K3 by Moonshot, category rank #5; source ranks: OpenRouter #6, Artificial Analysis #10, LLM Stats #8, Design Arena #1, LiveBench #10
- Muse Spark 1.3 by Meta, category rank #6; source ranks: Arena.ai #8, Artificial Analysis #4, LLM Stats #6, Design Arena #2, Vals.ai #5, LiveBench #4
- Claude Mythos 5.1 by Anthropic, category rank #7; source ranks: Vellum #2
- Claude Opus 4.6 by Anthropic, category rank #8; source ranks: Arena.ai #2
- GPT-5.6 Sol by OpenAI, category rank #9; source ranks: OpenRouter #5, Artificial Analysis #5, LLM Stats #3, Design Arena #5, Vals.ai #6, LiveBench #6
- Claude Opus 4.7 by Anthropic, category rank #10; source ranks: Arena.ai #3
- Claude Sonnet 5 by Anthropic, category rank #11; source ranks: OpenRouter #3
- Claude Mythos by Anthropic, category rank #12; source ranks: LLM Stats #4
- Claude Mythos 5 by Anthropic, category rank #13; source ranks: Vellum #4
- Claude Sonnet 4.6 by Anthropic, category rank #14; source ranks: OpenRouter #4
- Muse Spark 1.2 by Meta, category rank #15; source ranks: Arena.ai #4
Coding
- Claude Fable 5.1 by Anthropic, category rank #1; source ranks: Arena.ai #2, Artificial Analysis #1, Design Arena #6, LiveBench #1
- Claude Opus 5 by Anthropic, category rank #2; source ranks: OpenRouter #1, Arena.ai #3, Design Arena #7, Vals.ai #1
- GPT-6 Astra by OpenAI, category rank #3; source ranks: OpenRouter #2, Arena.ai #1
- GPT-5.6 Sol by OpenAI, category rank #4; source ranks: OpenRouter #4, Design Arena #4, Vellum #1, LiveBench #3
- Muse Spark 1.3 by Meta, category rank #5; source ranks: Arena.ai #8, Artificial Analysis #5, Design Arena #1
- Claude Fable 5 by Anthropic, category rank #6; source ranks: Arena.ai #10, Artificial Analysis #2, Vellum #3, LiveBench #2
- Claude Mythos 5 by Anthropic, category rank #7; source ranks: Vellum #2
- DeepSeek V4 Pro by DeepSeek, category rank #8; source ranks: Vals.ai #2
- Kimi K3 by Moonshot, category rank #9; source ranks: OpenRouter #5, Arena.ai #5, Artificial Analysis #6, Design Arena #3, Vals.ai #3
- GLM-5.3 by Z.ai, category rank #10; source ranks: OpenRouter #3, Artificial Analysis #7
- GPT-5.6 Luna by OpenAI, category rank #11; source ranks: OpenRouter #7, Vellum #4, LiveBench #5
- Claude Opus 4.8 by Anthropic, category rank #12; source ranks: OpenRouter #8, Vellum #5, Vals.ai #4, LiveBench #10
- Gemini 3.7 Flash by Google, category rank #13; source ranks: Artificial Analysis #4, Design Arena #10
- GPT 5.2 codex by OpenAI, category rank #14; source ranks: LiveBench #4
- Qwen3.8 Max by Alibaba, category rank #15; source ranks: Arena.ai #4
Agent
- GPT-6 Astra by OpenAI, category rank #1; source ranks: OpenRouter #1, Arena.ai #2, Design Arena #1, Vellum #2
- Claude Fable 5.1 by Anthropic, category rank #2; source ranks: OpenRouter #10, Arena.ai #1, Design Arena #2, Vellum #3, LiveBench #2
- GLM-5.3 by Z.ai, category rank #3; source ranks: OpenRouter #5, Vellum #1
- DeepSeek V4.1 Flash by DeepSeek, category rank #4; source ranks: LiveBench #1
- Muse Spark 1.2 by Meta, category rank #5; source ranks: Vals.ai #1
- Claude Opus 5 by Anthropic, category rank #6; source ranks: OpenRouter #2, Arena.ai #3, Design Arena #6, Vals.ai #2, LiveBench #3
- Kimi K3 by Moonshot, category rank #7; source ranks: OpenRouter #4, Arena.ai #8, Design Arena #3, LiveBench #9
- GPT-5.6 Sol by OpenAI, category rank #8; source ranks: OpenRouter #3, Arena.ai #7, Design Arena #10
- Gemini 3.5 Flash by Google, category rank #9; source ranks: Vals.ai #3
- Claude Opus 4.8 by Anthropic, category rank #10; source ranks: OpenRouter #6, Arena.ai #6, Vals.ai #4
- Muse Spark 1.3 by Meta, category rank #11; source ranks: Design Arena #4, LiveBench #7
- Claude Mythos 5.1 by Anthropic, category rank #12; source ranks: Vellum #4
- DeepSeek V4 Flash by DeepSeek, category rank #13; source ranks: LiveBench #4
- qwen3.8 by Alibaba, category rank #14; source ranks: Design Arena #5, LiveBench #5
- Claude Fable 5 by Anthropic, category rank #15; source ranks: Arena.ai #5, Design Arena #8, LiveBench #8
Reasoning
- GPT-6 Astra by OpenAI, category rank #1; source ranks: OpenRouter #6, Vellum #2, LiveBench #1
- Claude Opus 5 by Anthropic, category rank #2; source ranks: OpenRouter #1, LiveBench #4
- Claude Sonnet 5 by Anthropic, category rank #3; source ranks: OpenRouter #4, Vellum #1
- Kimi K3 by Moonshot, category rank #4; source ranks: OpenRouter #2, LiveBench #5
- Claude Fable 5.1 by Anthropic, category rank #5; source ranks: LiveBench #2
- GPT-5.6 Sol by OpenAI, category rank #6; source ranks: OpenRouter #3, Vellum #4, LiveBench #3
- Claude 3 Opus by Anthropic, category rank #7; source ranks: Vellum #3
- Claude Opus 4.8 by Anthropic, category rank #8; source ranks: OpenRouter #5
- Gemini 3.1 Pro by Google, category rank #9; source ranks: Vellum #5
- GPT-5.6 Terra by OpenAI, category rank #10; source ranks: LiveBench #6
- Claude Sonnet 4.6 by Anthropic, category rank #11; source ranks: OpenRouter #7
- Grok 4.6 by xAI, category rank #12; source ranks: LiveBench #7
- Claude Fable 5 by Anthropic, category rank #13; source ranks: OpenRouter #8
- smaug agentic, category rank #14; source ranks: LiveBench #8
- GLM-5.2 by Z.ai, category rank #15; source ranks: OpenRouter #9
Math
- Claude Opus 5 by Anthropic, category rank #1; source ranks: OpenRouter #1, Vals.ai #2, LiveBench #7
- AlephProver by Aleph, category rank #2; source ranks: Vals.ai #1
- Claude Fable 5.1 by Anthropic, category rank #3; source ranks: LiveBench #1
- Kimi K3 by Moonshot, category rank #4; source ranks: OpenRouter #2, Vals.ai #4
- GPT-6 Astra by OpenAI, category rank #5; source ranks: OpenRouter #7, LiveBench #2
- GPT-5.6 Sol by OpenAI, category rank #6; source ranks: OpenRouter #3, Vals.ai #6, LiveBench #3
- Claude Fable 5 by Anthropic, category rank #7; source ranks: Vals.ai #3, LiveBench #4
- qwen3.8 by Alibaba, category rank #8; source ranks: OpenRouter #4
- DeepSeek V4 Flash by DeepSeek, category rank #9; source ranks: OpenRouter #5
- Harmonic’s Aristotle by Harmonic, category rank #10; source ranks: Vals.ai #5
- Muse Spark 1.3 by Meta, category rank #11; source ranks: LiveBench #5
- Claude Opus 4.8 by Anthropic, category rank #12; source ranks: OpenRouter #6
- GPT-5.5 by OpenAI, category rank #13; source ranks: LiveBench #6
- Aristotle by Harmonic, category rank #14; source ranks: Vals.ai #7
- GLM-5.3 by Z.ai, category rank #15; source ranks: OpenRouter #8
Vision / Multimodal
- Claude Fable 5 by Anthropic, category rank #1; source ranks: Arena.ai #1, Vals.ai #2
- Claude Opus 5 by Anthropic, category rank #2; source ranks: Arena.ai #1, Vals.ai #3
- Kimi K3 by Moonshot, category rank #3; source ranks: Vals.ai #1
- Claude Fable 5.1 by Anthropic, category rank #4; source ranks: Arena.ai #2
- qwen3.8 by Alibaba, category rank #5; source ranks: Arena.ai #2
- Claude Opus 4.6 by Anthropic, category rank #6; source ranks: Arena.ai #3
- Claude Opus 4.7 by Anthropic, category rank #7; source ranks: Arena.ai #3
- GPT-5.6 Sol by OpenAI, category rank #8; source ranks: Arena.ai #10, Vals.ai #4
- Muse Spark 1.3 by Meta, category rank #9; source ranks: Arena.ai #6
- Muse Spark by Meta, category rank #10; source ranks: Arena.ai #7
- GPT-5.5 by OpenAI, category rank #11; source ranks: Arena.ai #8
- Muse Spark 1.2 by Meta, category rank #12; source ranks: Arena.ai #9
Search / Browsing
- GPT-5.6 Sol by OpenAI, category rank #1; source ranks: OpenRouter #5, Arena.ai #1, Artificial Analysis #7, Vellum #1
- Kimi K3 by Moonshot, category rank #2; source ranks: OpenRouter #1, Artificial Analysis #8, Vellum #3
- Claude Fable 5.1 by Anthropic, category rank #3; source ranks: Artificial Analysis #1
- GPT-6 Astra by OpenAI, category rank #4; source ranks: OpenRouter #3, Artificial Analysis #2, Vellum #2
- Claude Opus 5 by Anthropic, category rank #5; source ranks: OpenRouter #2, Artificial Analysis #3, Vellum #4
- Claude Opus 4.6 by Anthropic, category rank #6; source ranks: Arena.ai #2
- GPT-5.5 by OpenAI, category rank #7; source ranks: Arena.ai #3
- Grok 4.6 by xAI, category rank #8; source ranks: OpenRouter #9, Artificial Analysis #4
- Claude Opus 4.7 by Anthropic, category rank #9; source ranks: Arena.ai #4
- GPT-5.6 Terra by OpenAI, category rank #10; source ranks: OpenRouter #4
- Claude Fable 5 by Anthropic, category rank #11; source ranks: OpenRouter #7, Arena.ai #5, Vellum #5
- Gemini 3.8 Flash by Google, category rank #12; source ranks: Artificial Analysis #5
- Claude Sonnet 5 by Anthropic, category rank #13; source ranks: OpenRouter #6
- ernie 5.1 by Baidu, category rank #14; source ranks: Arena.ai #6
- Muse Spark 1.3 by Meta, category rank #15; source ranks: Artificial Analysis #6
Image Generation
- GPT Image 2.5 Sunburst by OpenAI, category rank #1; source ranks: Arena.ai #1, Design Arena #1
- GPT Image 2.5 Flare by OpenAI, category rank #2; source ranks: Arena.ai #2, Design Arena #4
- riverflow 2.5 pro, category rank #3; source ranks: Design Arena #2
- GPT Image 2 by OpenAI, category rank #4; source ranks: Arena.ai #3, Design Arena #3
- mai image 2.6 by Microsoft, category rank #5; source ranks: Arena.ai #4, Design Arena #6
- carillon 2, category rank #6; source ranks: Design Arena #5
- grok imagine image 2.0 by xAI, category rank #7; source ranks: Arena.ai #5
- babylon, category rank #8; source ranks: Design Arena #6
- reve 2.1 by Reve, category rank #9; source ranks: Arena.ai #6
- grok imagine image 2 by xAI, category rank #10; source ranks: Design Arena #7
- muse image by Meta, category rank #11; source ranks: Arena.ai #7
- reve 2.0 by Reve, category rank #12; source ranks: Arena.ai #8
- Gemini 3.1 flash image (nano banana 2) [web search] by Google, category rank #13; source ranks: Arena.ai #9
- mai image 2.6 flash by Microsoft, category rank #14; source ranks: Design Arena #9
- chestnut, category rank #15; source ranks: Design Arena #10
Image Edit
- GPT Image 2.5 Sunburst by OpenAI, category rank #1; source ranks: Arena.ai #1, Design Arena #1
- GPT Image 2.5 Flare by OpenAI, category rank #2; source ranks: Arena.ai #2, Design Arena #2
- GPT Image 2 by OpenAI, category rank #3; source ranks: Arena.ai #3, Design Arena #3
- grok imagine image 2.0 by xAI, category rank #4; source ranks: Arena.ai #4
- riverflow 2.5 pro edit, category rank #5; source ranks: Design Arena #4
- babylon 2, category rank #6; source ranks: Design Arena #5
- mai image 2.6 by Microsoft, category rank #7; source ranks: Arena.ai #5
- carillon, category rank #8; source ranks: Design Arena #6
- muse image by Meta, category rank #9; source ranks: Arena.ai #6
- hazel, category rank #10; source ranks: Design Arena #7
- mai image 2.5 by Microsoft, category rank #11; source ranks: Arena.ai #7
- muse image 1.0 by Meta, category rank #12; source ranks: Design Arena #8
- seedream 5.0 pro by ByteDance, category rank #13; source ranks: Arena.ai #8
- Gemini 3 Pro by Google, category rank #14; source ranks: Arena.ai #9
- grok imagine image 2 auto by xAI, category rank #15; source ranks: Design Arena #9
Video
- Gemini Omni Flash by Google, category rank #1; source ranks: Arena.ai #2, Design Arena #1
- fig, category rank #2; source ranks: Design Arena #1
- Gemini Omni 1.1 Flash by Google, category rank #3; source ranks: Arena.ai #1
- wan v3.0 t2v by Alibaba, category rank #4; source ranks: Design Arena #2
- minimax h3 by MiniMax, category rank #5; source ranks: Arena.ai #8, Design Arena #3
- wan3.0 by Alibaba, category rank #6; source ranks: Arena.ai #3
- flux 3 video by Black Forest Labs, category rank #7; source ranks: Arena.ai #4, Design Arena #4
- seedance 2.5 by ByteDance, category rank #8; source ranks: Design Arena #4
- grok imagine video 1.5 agent by xAI, category rank #9; source ranks: Arena.ai #5
- tomato, category rank #10; source ranks: Design Arena #5
- dreamina seedance 2.5 720p by ByteDance, category rank #11; source ranks: Arena.ai #6
- seedance 2.0 by ByteDance, category rank #12; source ranks: Design Arena #6
- dreamina seedance 2.0 720p by ByteDance, category rank #13; source ranks: Arena.ai #7
- seedance 2.0 fast by ByteDance, category rank #14; source ranks: Design Arena #7
- happy horse 1.1, category rank #15; source ranks: Design Arena #8
Video Edit
- fig, category rank #1; source ranks: Design Arena #1
- wan3.0 by Alibaba, category rank #2; source ranks: Arena.ai #1
- minimax h3 by MiniMax, category rank #3; source ranks: Arena.ai #3, Design Arena #2
- dreamina seedance 2.5 720p by ByteDance, category rank #4; source ranks: Arena.ai #2
- Gemini Omni Flash by Google, category rank #5; source ranks: Arena.ai #4, Design Arena #3
- dreamina seedance 2.0 720p by ByteDance, category rank #6; source ranks: Arena.ai #5
- flux 3 video edit by Black Forest Labs, category rank #7; source ranks: Design Arena #5
- happyhorse 1.0 by HappyHorse, category rank #8; source ranks: Arena.ai #6
- wan v2.7 v2v by Alibaba, category rank #9; source ranks: Design Arena #6
- grok imagine video by xAI, category rank #10; source ranks: Arena.ai #7
- happy horse 1.0, category rank #11; source ranks: Design Arena #7
- aleph2 by Aleph, category rank #12; source ranks: Design Arena #8
- kling o3 pro by OpenAI, category rank #13; source ranks: Arena.ai #8
- kling o1 pro by OpenAI, category rank #14; source ranks: Arena.ai #9
- libra, category rank #15; source ranks: Design Arena #9
Design / UI
- GPT-6 Astra by OpenAI, category rank #1; source ranks: OpenRouter #1, Arena.ai #1, Design Arena #1
- Muse Spark 1.3 by Meta, category rank #2; source ranks: Arena.ai #8, Design Arena #1
- GPT Image 2 by OpenAI, category rank #3; source ranks: Design Arena #1
- Claude Opus 5 by Anthropic, category rank #4; source ranks: OpenRouter #2, Arena.ai #3, Design Arena #5
- Claude Fable 5.1 by Anthropic, category rank #5; source ranks: Arena.ai #2, Design Arena #6
- GPT Image 2.5 Sunburst by OpenAI, category rank #6; source ranks: Design Arena #2
- Kimi K3 by Moonshot, category rank #7; source ranks: OpenRouter #4, Arena.ai #5, Design Arena #3
- carillon 2, category rank #8; source ranks: Design Arena #3
- GPT-5.6 Sol by OpenAI, category rank #9; source ranks: OpenRouter #7, Design Arena #4
- babylon, category rank #10; source ranks: Design Arena #4
- Qwen3.8 Max by Alibaba, category rank #11; source ranks: Arena.ai #4
- GLM-5.2 by Z.ai, category rank #12; source ranks: OpenRouter #5
- GPT Image 2.5 Flare by OpenAI, category rank #13; source ranks: Design Arena #5
- qwen3.8 by Alibaba, category rank #14; source ranks: Arena.ai #6, Design Arena #6
- Claude Sonnet 5 by Anthropic, category rank #15; source ranks: OpenRouter #6
Data Analysis
- Claude Fable 5.1 by Anthropic, category rank #1; source ranks: Artificial Analysis #1, Design Arena #1, LiveBench #4
- GPT-6 Astra by OpenAI, category rank #2; source ranks: OpenRouter #5, Artificial Analysis #3, Design Arena #6, LiveBench #1
- GPT-5.6 Sol by OpenAI, category rank #3; source ranks: OpenRouter #1, Artificial Analysis #5, Design Arena #8, LiveBench #6
- Claude Opus 5 by Anthropic, category rank #4; source ranks: OpenRouter #2, Artificial Analysis #2, Design Arena #4
- GPT-5.5 by OpenAI, category rank #5; source ranks: LiveBench #2
- Muse Spark 1.2 by Meta, category rank #6; source ranks: Design Arena #2
- Claude Fable 5 by Anthropic, category rank #7; source ranks: Artificial Analysis #4, Design Arena #9, LiveBench #3
- Kimi K3 by Moonshot, category rank #8; source ranks: OpenRouter #7, Artificial Analysis #7, Design Arena #3
- Claude Sonnet 4.6 by Anthropic, category rank #9; source ranks: OpenRouter #3
- GPT-5.6 Luna by OpenAI, category rank #10; source ranks: OpenRouter #4
- Muse Spark 1.3 by Meta, category rank #11; source ranks: Design Arena #5, LiveBench #7
- smaug agentic, category rank #12; source ranks: LiveBench #5
- Claude Sonnet 5 by Anthropic, category rank #13; source ranks: OpenRouter #6
- Grok 4.6 by xAI, category rank #14; source ranks: Artificial Analysis #6
- Gemini 3.7 Flash by Google, category rank #15; source ranks: Design Arena #7
Terminal / Computer Use
- GPT-5.6 Sol by OpenAI, category rank #1; source ranks: OpenRouter #8, Vellum #1, Vals.ai #2
- GPT-6 Astra by OpenAI, category rank #2; source ranks: OpenRouter #4, Vals.ai #1
- Claude Fable 5 by Anthropic, category rank #3; source ranks: Vellum #1
- DeepSeek V4 Pro by DeepSeek, category rank #4; source ranks: OpenRouter #1
- Claude Opus 5 by Anthropic, category rank #5; source ranks: OpenRouter #2, Vals.ai #4
- Claude Opus 4.8 by Anthropic, category rank #6; source ranks: OpenRouter #5, Vellum #2, Vals.ai #5
- Kimi K3 by Moonshot, category rank #7; source ranks: OpenRouter #6, Vellum #2
- Gemini 3.7 Flash by Google, category rank #8; source ranks: OpenRouter #3, Vellum #4
- Claude Fable 5.1 by Anthropic, category rank #9; source ranks: Vals.ai #3
- Claude Mythos 5 by Anthropic, category rank #10; source ranks: Vellum #3
- Claude Sonnet 5 by Anthropic, category rank #11; source ranks: Vellum #3
- GPT-5.5 by OpenAI, category rank #12; source ranks: Vellum #4
- Claude Sonnet 4.6 by Anthropic, category rank #13; source ranks: Vellum #5
- GLM-5.3 by Z.ai, category rank #14; source ranks: OpenRouter #7
- Gemini 3.8 Flash by Google, category rank #15; source ranks: OpenRouter #9
Finance
- GPT-6 Astra by OpenAI, category rank #1; source ranks: OpenRouter #1
- Muse Spark 1.2 by Meta, category rank #2; source ranks: Vals.ai #1
- Claude Opus 5 by Anthropic, category rank #3; source ranks: OpenRouter #3, Vals.ai #2
- GPT-5.6 Sol by OpenAI, category rank #4; source ranks: OpenRouter #2
- Gemini 3.5 Flash by Google, category rank #5; source ranks: Vals.ai #3
- Claude Opus 4.8 by Anthropic, category rank #6; source ranks: OpenRouter #4, Vals.ai #4
- GLM-5.2 by Z.ai, category rank #7; source ranks: OpenRouter #5
- Kimi K3 by Moonshot, category rank #8; source ranks: OpenRouter #6
- DeepSeek V4 Flash by DeepSeek, category rank #9; source ranks: OpenRouter #7
- DeepSeek V4 Pro by DeepSeek, category rank #10; source ranks: OpenRouter #8
- Claude Sonnet 5 by Anthropic, category rank #11; source ranks: OpenRouter #10
Legal
- Muse Spark 1.2 by Meta, category rank #1; source ranks: Vals.ai #1
- Muse Spark 1.3 by Meta, category rank #2; source ranks: Vals.ai #1
- Claude Opus 5 by Anthropic, category rank #3; source ranks: Vals.ai #2
- Claude Fable 5.1 by Anthropic, category rank #4; source ranks: Vals.ai #3
- Kimi K3 by Moonshot, category rank #5; source ranks: Vals.ai #3
- Claude Fable 5 by Anthropic, category rank #6; source ranks: Vals.ai #4
- DeepSeek V4 by DeepSeek, category rank #7; source ranks: Vals.ai #4
- GPT-5.6 Sol by OpenAI, category rank #8; source ranks: Vals.ai #5
- Grok 4.6 by xAI, category rank #9; source ranks: Vals.ai #5
- Claude Opus 4.8 by Anthropic, category rank #10; source ranks: Vals.ai #7