General Writing on Arena-Hard Prompt
72.6ScoreGemini-3.0 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3.0 ProVariant=Pro2026.01 | 72.6 | |
| Kimi-K2 ThinkingThinking Mode=true2026.01 | 71.9 | |
| GPT-5 HighVariant=High2026.01 | 71.9 | |
| Claude Sonnet 4.5Variant=Sonnet 4.52026.01 | 63.3 | |
| MiMo-V2-FlashVariant=Flash2026.01 | 54.1 | |
| DeepSeek-V3.2 ThinkingThinking Mode=true2026.01 | 53.4 |