Excel Modeling Benchmark Misc
Professional Work · 2026-07-01
This row reports the category score for miscellaneous financial-modeling tasks in Excel Modeling Benchmark.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 4 Argon | 74.0 |
| Claude Fable 5.1 | 72.2 |
| Claude Fable 5 | 71.4 |
| Claude Opus 5.5 | 71.0 |
| Gemini 3.7 Flash | 70.9 |
| Gemini 3.8 Flash | 70.4 |
| GPT-5.6 Luna | 70.1 |
| GPT-5.6 Terra | 69.5 |
| Claude Sonnet 5.5 | 69.1 |
| GPT-5.6 Sol | 68.7 |
| GPT-6 Luna | 68.6 |
| Claude Opus 5 | 66.9 |
| Qwen3.8 Max (0902) | 66.8 |
| GPT-6 Sol | 65.0 |
| Grok 4.7 | 65.0 |
| GPT-5.5 | 64.6 |
| Muse Spark 1.3 | 64.5 |
| Gemini 3.6 Flash | 64.4 |
| Muse Wonder Full | 64.2 |
| MiMo-V2.6-Flash | 63.6 |
| Ember-1 | 63.1 |
| Kimi K3 | 63.0 |
| Gemini 3.5 Flash | 62.2 |
| Sonnet 4.6 | 61.7 |
| GPT-6.1 Sol | 61.6 |
| DeepSeek V4.1 Flash 1017 | 60.9 |
| GLM-5.2 | 60.8 |
| Qwen3.8-Max | 60.7 |
| Grok 4.6 | 60.3 |
| GPT-6 Astra | 59.8 |
| Opus 4.8 | 59.4 |
| Qwen3.8 27B | 59.1 |
| Qwen3.7-Max (source unspecified) | 57.7 |
| Hy4 Preview | 57.7 |
| DeepSeek-V4-Pro | 57.6 |
| DeepSeek-V4-Flash-0731 | 57.6 |
| Muse Wonder | 56.9 |
| GLM-5.3 | 56.4 |
| Kimi K2.6 | 54.6 |
| Opus 4.7 | 54.3 |