Excel Modeling Benchmark v1.1 LBO
Professional Work · 2026-10-19
Category score for leveraged-buyout tasks in Excel Modeling Benchmark v1.1.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Sonnet 5.5 | 68.7 |
| Claude Opus 5.5 | 68.3 |
| Claude Fable 5.1 | 68.0 |
| Gemini 4 Argon | 67.2 |
| Muse Wonder | 64.2 |
| GPT-6.1 Sol | 63.8 |
| Muse Wonder Full | 63.5 |
| DeepSeek V4.1 Flash 1017 | 62.5 |
| Gemini 3.8 Flash | 62.2 |
| MiMo-V2.6-Pro | 61.6 |
| GLM-5.3 | 61.4 |
| Step 5 Preview | 61.2 |
| GPT-6 Astra | 61.2 |
| Kimi K3 | 60.7 |
| Mistral Large 4 Preview | 60.6 |
| Grok 4.7 | 60.6 |
| MiMo-V2.6-Flash | 59.5 |
| MiniMax M3.1 Flash | 58.6 |
| GPT-6 Luna | 57.9 |
| Hy4 Preview | 57.8 |
| DeepSeek V4.1 Flash | 56.4 |
| DeepSeek V4 Pro 0813 | 52.8 |
| Qwen3.8-Max | 50.4 |
| GLM-5.3 Flash | 50.0 |
| Beam 1.0 501B A23B | 49.8 |
| Claude Haiku 5.5 | 49.1 |
| Muse Spark Open | 48.3 |
| Mercury 3 | 47.6 |
| MiniMax M3 | 41.6 |
| Inkling-Small | 26.8 |
| Inkling | 20.3 |