Leaderboard bars
18 ranked models · higher is better
View accessible chart data
| Model | Rank | Provider | Score |
|---|---|---|---|
| Muse Spark 1.1 | #1 | Meta | 75.6% |
| Kimi K3 | #2 | Moonshot AI | 73.2% |
| Claude Opus 4.8 | #3 | Anthropic | 59.9% |
| GPT-5.6 Sol | #4 | OpenAI | 58% |
| Gemini 3.5 Flash | #5 | 56.5% | |
| GPT-5.5 | #6 | OpenAI | 55.6% |
| GPT-5.4 | #7 | OpenAI | 54.6% |
| GPT-5.6 Luna | #8 | OpenAI | 53.4% |
| GPT-5.6 Terra | #9 | OpenAI | 53.1% |
| GLM-5.2 | #10 | Z.AI | 48.2% |
| DeepSeek V4 Pro | #11 | DeepSeek | 46.3% |
| MiniMax M2.7 | #12 | MiniMax | 46.3% |
| Claude Opus 4.5 | #13 | Anthropic | 43.5% |
| DeepSeek V4 Flash | #14 | DeepSeek | 40.7% |
| Qwen3.6 Plus | #15 | Alibaba Cloud | 39.8% |
| GLM-5 | #16 | Z.AI | 38% |
| GPT-5.4 nano | #17 | OpenAI | 35.5% |
| Kimi K2.5 | #18 | Moonshot AI | 27.8% |

