Excel Modeling Benchmark v1.1 Misc
Professional Work · 2026-10-19
Category score for miscellaneous financial-modeling tasks (such as cash-flow, waterfall and project-finance models) in Excel Modeling Benchmark v1.1.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 4 Argon | 73.0 |
| Claude Fable 5.1 | 71.4 |
| Claude Opus 5.5 | 71.0 |
| Muse Wonder Full | 70.9 |
| GPT-6 Luna | 69.5 |
| Gemini 3.8 Flash | 68.9 |
| Claude Sonnet 5.5 | 68.8 |
| Grok 4.7 | 68.2 |
| Kimi K3 | 67.6 |
| MiMo-V2.6-Flash | 67.3 |
| Hy4 Preview | 67.0 |
| Step 5 Preview | 65.8 |
| DeepSeek V4.1 Flash 1017 | 65.7 |
| Qwen3.8-Max | 65.0 |
| MiniMax M3.1 Flash | 64.9 |
| Mistral Large 4 Preview | 64.8 |
| DeepSeek V4 Pro 0813 | 63.6 |
| Muse Wonder | 63.0 |
| Beam 1.0 501B A23B | 62.6 |
| DeepSeek V4.1 Flash | 62.5 |
| GPT-6.1 Sol | 61.5 |
| GLM-5.3 | 60.8 |
| GPT-6 Astra | 60.6 |
| Muse Spark Open | 60.3 |
| Mercury 3 | 58.0 |
| Claude Haiku 5.5 | 57.0 |
| GLM-5.3 Flash | 56.7 |
| MiniMax M3 | 53.1 |
| Inkling | 49.5 |
| Inkling-Small | 39.0 |
| MiMo-V2.6-Pro | 38.7 |