Excel Modeling Benchmark M&A
Professional Work · 2026-07-01
This row reports the category score for merger-and-acquisition tasks in Excel Modeling Benchmark.
Top models (higher is better)
| Model | Score |
|---|---|
| Muse Spark 1.3 | 84.2 |
| GPT-6.1 Sol | 83.9 |
| GPT-5.6 Sol | 83.9 |
| Gemini 3.7 Flash | 83.4 |
| GPT-6 Astra | 83.1 |
| GPT-6 Sol | 83.0 |
| Claude Sonnet 5.5 | 83.0 |
| Claude Opus 5.5 | 82.3 |
| Claude Fable 5.1 | 81.2 |
| Gemini 3.8 Flash | 81.0 |
| Gemini 4 Argon | 81.0 |
| Claude Fable 5 | 80.6 |
| Claude Opus 5 | 80.4 |
| Opus 4.8 | 80.1 |
| Muse Wonder Full | 78.3 |
| GPT-5.6 Terra | 77.6 |
| Qwen3.8 Max (0902) | 77.3 |
| Muse Wonder | 76.9 |
| Grok 4.7 | 76.3 |
| Sonnet 5 | 75.8 |
| Gemini 3.6 Flash | 75.6 |
| MiMo-V2.6-Pro | 74.4 |
| Kimi K3 | 72.7 |
| GPT-6 Luna | 72.1 |
| Opus 4.7 | 71.7 |
| Sonnet 4.6 | 70.5 |
| GPT-5.6 Luna | 69.6 |
| Gemini 3.5 Flash | 68.4 |
| Hy4 Preview | 68.0 |
| Qwen3.7-Max (source unspecified) | 67.1 |
| GPT-5.5 | 66.8 |
| Ember-1 | 66.7 |
| GLM-5.3 Flash | 65.3 |
| Qwen3.8 27B | 64.8 |
| Grok 4.5 | 64.6 |
| Step 5 Preview | 64.6 |
| Kimi K2.6 | 64.2 |
| MiMo-V2.5-Pro | 64.1 |
| MiMo-V2.6-Flash | 64.1 |
| GLM-5.2 | 63.9 |