| 順位 | モデル | |
|---|---|---|
| #1 | Anthropic Claude Opus 4.5 | 89.5% |
| #2 | Gemini 3 Flash | 89.0% |
| #3 | Anthropic Claude Opus 4.1 | 88.0% |
| #4 | Anthropic Claude Sonnet 4.5 | 87.5% |
| #5 | Anthropic Claude Opus 4 | 87.3% |
| #6 | DeepSeek DeepSeek V3.2 | 86.2% |
| #7 | Gemini 2.5 Pro | 86.2% |
| #8 | Grok Grok 4.1 Fast (Reasoning) | 85.4% |
| #9 | Anthropic Claude Sonnet 4 | 84.2% |
| #10 | LG AI Research K-EXAONE | 83.8% |
| #11 | Gemini 2.5 Flash | 83.2% |
| #12 | Baidu ERNIE 5.0 Thinking | 83.0% |
| #13 | OpenAI GPT-5 | 82.0% |
| #14 | Meta Llama 4 Maverick | 80.9% |
| #15 | OpenAI GPT-4.1 | 80.6% |
| #16 | Gemini 2.5 Flash Lite | 79.6% |
| #17 | Baidu ERNIE 4.5 300B A47B | 77.6% |
| #18 | OpenAI GPT OSS 120B | 77.5% |
| #19 | OpenAI GPT-5 Mini | 77.5% |
| #20 | OpenAI GPT-5 Nano | 77.2% |
| #21 | Anthropic Claude Haiku 4.5 | 76.0% |
| #22 | Meta Llama 4 Scout | 75.2% |
| #23 | Grok Grok 4.1 Fast | 74.3% |
| #24 | Amazon Nova 2 Lite | 74.3% |
| #25 | Mistral AI Mistral Small 4 | 41.9% |