数学分野の専門家プロンプトにおけるArena Eloスコアです。
Anthropic
Claude Opus 4.6
OpenAI
GPT-5.4
GPT-5.4 Pro
Claude Opus 4.7
Google
Gemini 3.1 Pro
Claude Sonnet 4.6
Moonshot AI
Kimi K2.5
Kimi K2.6
Z.ai
GLM-5.1
Gemini 3 Flash
Gemma 4 31B
Claude Opus 4.5
Claude Sonnet 4.5
GLM-5
Meta
Muse Spark
GPT-5.4 Mini
Grok
Grok 4.20
Grok 4.20 (Reasoning)
Xiaomi
MiMo-V2-Pro
Alibaba
Qwen3.5 397B A17B
Qwen3.6 Plus
Gemini 2.5 Pro
DeepSeek
DeepSeek V4 Pro
Claude Opus 4.1
DeepSeek V4 Flash
GPT-5.4 Nano
GPT-5
Meituan
Longcat Flash Chat
DeepSeek V3.2
Baidu
ERNIE 5.0 Thinking
Gemini 3.1 Flash Lite
Claude Opus 4
Grok 4.1 Fast
Grok 4.1 Fast (Reasoning)
Claude Haiku 4.5
Gemini 2.5 Flash
MiniMax
MiniMax M2.5
MiniMax M2.7
Claude Sonnet 4
GPT-5 Mini
NVIDIA
Nemotron 3 Super
GPT OSS 120B
Arcee AI
Trinity Large Thinking
Gemini 2.5 Flash Lite
GPT-5 Nano
Amazon
Nova 2 Lite
Llama 4 Maverick
Llama 4 Scout
GPT-4.1