Excel Modeling Benchmark v1.1 M&A
Professional Work · 2026-10-19
Category score for merger-and-acquisition tasks in Excel Modeling Benchmark v1.1.
Top models (higher is better)
| Model | Score |
|---|---|
| Muse Wonder Full | 83.4 |
| GPT-6.1 Sol | 83.1 |
| GPT-6 Astra | 82.9 |
| Claude Sonnet 5.5 | 82.3 |
| Claude Opus 5.5 | 82.1 |
| MiMo-V2.6-Pro | 80.8 |
| Grok 4.7 | 80.7 |
| Claude Fable 5.1 | 80.5 |
| Muse Wonder | 80.4 |
| Gemini 4 Argon | 80.2 |
| Gemini 3.8 Flash | 79.9 |
| GLM-5.3 | 79.2 |
| Hy4 Preview | 76.8 |
| Kimi K3 | 76.6 |
| DeepSeek V4.1 Flash | 75.7 |
| Beam 1.0 501B A23B | 75.7 |
| GPT-6 Luna | 74.8 |
| Step 5 Preview | 74.7 |
| MiMo-V2.6-Flash | 74.6 |
| MiniMax M3.1 Flash | 74.4 |
| Mistral Large 4 Preview | 74.1 |
| GLM-5.3 Flash | 73.6 |
| DeepSeek V4.1 Flash 1017 | 73.1 |
| Qwen3.8-Max | 73.0 |
| DeepSeek V4 Pro 0813 | 72.6 |
| Muse Spark Open | 71.1 |
| MiniMax M3 | 70.6 |
| Claude Haiku 5.5 | 62.9 |
| Mercury 3 | 57.8 |
| Inkling | 52.9 |
| Inkling-Small | 42.1 |