Excel Modeling Benchmark Template
Professional Work · 2026-07-01
Template-mode score on Excel Modeling Benchmark, where agents complete a stripped template workbook and are graded against the gold workbook.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5 | 77.0 |
| GPT-5.6 Sol | 75.3 |
| Claude Opus 5 | 74.7 |
| Opus 4.8 | 71.1 |
| GPT-5.6 Terra | 70.3 |
| Sonnet 5 | 68.0 |
| Gemini 3.6 Flash | 64.7 |
| GPT-5.6 Luna | 64.7 |
| Kimi K3 | 64.4 |
| Gemini 3.5 Flash | 62.5 |
| GPT-5.5 | 61.8 |
| GLM-5.2 | 55.8 |
| Kimi K2.6 | 55.7 |
| Sonnet 4.6 | 55.2 |
| MiMo-V2.5-Pro | 52.1 |
| Qwen3.7-Max | 51.8 |
| Muse Spark 1.1 | 49.4 |
| Gemini 3.1 Pro Preview | 47.2 |
| DeepSeek-V4-Pro | 46.1 |
| GPT-5.4 Nano | 45.1 |
| Qwen3.7-Plus | 41.5 |
| Gemini 3.5 Flash-Lite | 40.9 |
| Grok 4.5 | 38.3 |
| GPT-5.4 Mini | 36.0 |
| MiniMax M3 | 34.5 |
| Inkling | 32.5 |
| Inkling-Small | 18.2 |
| Gemini 3.1 Flash-Lite Preview | 8.1 |
| Grok 4.3 | 6.8 |