Excel Modeling Benchmark Operating
Professional Work · 2026-07-01
This row reports the category score for operating-model tasks in Excel Modeling Benchmark.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5.5 | 77.9 |
| GPT-6 Astra | 75.4 |
| Claude Fable 5.1 | 74.8 |
| GPT-6.1 Sol | 73.9 |
| Claude Opus 5 | 73.5 |
| GPT-6 Sol | 72.9 |
| Claude Fable 5 | 72.8 |
| GPT-5.6 Luna | 72.7 |
| Claude Sonnet 5.5 | 71.6 |
| GPT-6 Luna | 71.1 |
| Qwen3.8 Max (0902) | 69.5 |
| Gemini 4 Argon | 69.4 |
| Gemini 3.8 Flash | 69.1 |
| Muse Wonder Full | 68.6 |
| GPT-5.6 Terra | 68.3 |
| Grok 4.6 | 68.2 |
| GPT-5.6 Sol | 67.3 |
| Opus 4.8 | 66.7 |
| DeepSeek V4.1 Flash 1017 | 66.1 |
| DeepSeek V4.1 Flash | 66.0 |
| MiMo-V2.6-Pro | 65.5 |
| Sonnet 5 | 65.5 |
| Muse Wonder | 65.4 |
| Qwen3.8-Max | 65.1 |
| Hy4 Preview | 65.0 |
| GPT-5.5 | 64.5 |
| Grok 4.7 | 64.0 |
| Kimi K3 | 63.9 |
| Ember-1 | 63.7 |
| Muse Spark Open | 63.1 |
| Step 5 Preview | 63.1 |
| Gemini 3.6 Flash | 63.0 |
| GLM-5.2 | 62.9 |
| Mistral Large 4 Preview | 62.7 |
| MiMo-V2.6-Flash | 62.5 |
| GLM-5.3 Flash | 62.1 |
| Grok 4.5 | 61.9 |
| Muse Spark 1.3 | 61.5 |
| GLM-5.3 | 61.4 |
| Opus 4.7 | 61.2 |