Leaderboard bars
20 ranked models · higher is better
View accessible chart data
| Model | Rank | Provider | Score |
|---|---|---|---|
| Kimi K3 | #1 | Moonshot AI | 26.7% |
| Claude Fable 5 | #2 | Anthropic | 14.2% |
| Grok 4.5 | #3 | xAI | 13.3% |
| Muse Spark 1.1 | #4 | Meta | 8.3% |
| Claude Opus 4.8 | #5 | Anthropic | 7.5% |
| GLM-5.2 | #6 | Z.AI | 7.5% |
| MiniMax M3 | #7 | MiniMax | 6.7% |
| Claude Sonnet 5 | #8 | Anthropic | 5% |
| GPT-5.6 Luna | #9 | OpenAI | 5% |
| Claude Sonnet 4.6 | #10 | Anthropic | 4.2% |
| GPT-5.5 | #11 | OpenAI | 4.2% |
| DeepSeek V4 Pro | #12 | DeepSeek | 3.3% |
| MiMo-V2-Flash | #13 | Xiaomi | 3.3% |
| Nemotron 3 Ultra | #14 | NVIDIA | 3.3% |
| GPT-5.6 Terra | #15 | OpenAI | 2.5% |
| DeepSeek V4 Flash | #16 | DeepSeek | 1.7% |
| Gemini 3.5 Flash | #17 | 1.7% | |
| Qwen3.7-Plus | #18 | Alibaba Cloud | 1.7% |
| Kimi K2.7 Code | #19 | Moonshot AI | 0.8% |
| Mistral Medium 3.5 | #20 | Mistral AI | 0.8% |