Excel Modeling Benchmark LBO
Professional Work · 2026-07-01
This row reports the category score for leveraged buyout tasks in Excel Modeling Benchmark.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Sonnet 5.5 | 70.0 |
| Claude Fable 5.1 | 69.6 |
| Claude Opus 5.5 | 69.0 |
| Gemini 4 Argon | 68.5 |
| GPT-5.6 Sol | 67.2 |
| Claude Fable 5 | 65.9 |
| Qwen3.8 Max (0902) | 64.9 |
| GPT-6.1 Sol | 64.4 |
| MiMo-V2.6-Pro | 62.4 |
| GPT-6 Astra | 61.8 |
| Claude Opus 5 | 61.2 |
| Muse Wonder | 60.7 |
| Sonnet 5 | 60.0 |
| Muse Wonder Full | 59.6 |
| GPT-6 Sol | 59.4 |
| Gemini 3.7 Flash | 59.4 |
| Grok 4.6 | 59.3 |
| GPT-5.6 Luna | 59.3 |
| GPT-6 Luna | 59.1 |
| Step 5 Preview | 58.9 |
| Gemini 3.8 Flash | 58.6 |
| Ember-1 | 58.1 |
| GLM-5.3 | 58.0 |
| DeepSeek V4.1 Flash 1017 | 57.8 |
| Mistral Large 4 Preview | 57.5 |
| Muse Spark 1.3 | 57.3 |
| MiMo-V2.6-Flash | 56.9 |
| Grok 4.7 | 56.9 |
| Kimi K3 | 56.9 |
| Opus 4.7 | 56.4 |
| Hy4 Preview | 55.2 |
| Opus 4.8 | 54.4 |
| DeepSeek V4.1 Flash | 54.2 |
| Qwen3.8 27B | 53.7 |
| GPT-5.5 | 53.2 |
| Sonnet 4.6 | 52.5 |
| Gemini 3.6 Flash | 52.5 |
| GLM-5.2 | 51.8 |
| Muse Spark Open | 50.7 |
| GPT-5.6 Terra | 50.4 |