Excel Modeling Benchmark v1.1 Operating
Professional Work · 2026-10-19
Category score for operating-model tasks in Excel Modeling Benchmark v1.1.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5.5 | 77.7 |
| GPT-6 Astra | 75.5 |
| Claude Fable 5.1 | 75.2 |
| Muse Wonder Full | 74.6 |
| GPT-6.1 Sol | 74.4 |
| DeepSeek V4.1 Flash | 71.9 |
| MiMo-V2.6-Pro | 71.6 |
| Claude Sonnet 5.5 | 71.4 |
| GPT-6 Luna | 70.8 |
| Muse Wonder | 70.6 |
| Hy4 Preview | 70.2 |
| GLM-5.3 Flash | 70.1 |
| Kimi K3 | 69.9 |
| Gemini 4 Argon | 69.9 |
| GLM-5.3 | 69.5 |
| Qwen3.8-Max | 69.4 |
| Gemini 3.8 Flash | 69.2 |
| Step 5 Preview | 68.9 |
| Mistral Large 4 Preview | 68.8 |
| Grok 4.7 | 68.8 |
| Muse Spark Open | 68.6 |
| DeepSeek V4 Pro 0813 | 68.2 |
| MiMo-V2.6-Flash | 67.2 |
| MiniMax M3.1 Flash | 66.5 |
| DeepSeek V4.1 Flash 1017 | 66.0 |
| Beam 1.0 501B A23B | 65.1 |
| Claude Haiku 5.5 | 62.7 |
| MiniMax M3 | 62.3 |
| Mercury 3 | 61.7 |
| Inkling | 43.8 |
| Inkling-Small | 41.0 |