Excel Modeling Benchmark
Professional Work · 2026-07-01
Excel Modeling Benchmark evaluates agents on Excel-based financial modeling tasks, including template-based and scratch financial model construction scored against expert-authored reference workbooks and rubrics.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5 | 73.7 |
| Claude Opus 5 | 73.6 |
| GPT-5.6 Sol | 72.3 |
| Opus 4.8 | 69.4 |
| GPT-5.6 Terra | 67.6 |
| GPT-5.6 Luna | 67.1 |
| Kimi K3 | 66.4 |
| Sonnet 5 | 66.3 |
| Gemini 3.6 Flash | 65.4 |
| GPT-5.5 | 64.5 |
| Gemini 3.5 Flash | 63.5 |
| GLM-5.2 | 61.5 |
| Sonnet 4.6 | 60.2 |
| Kimi K2.6 | 57.9 |
| Qwen3.7-Max | 57.0 |
| Muse Spark 1.1 | 56.4 |
| MiMo-V2.5-Pro | 55.2 |
| Grok 4.5 | 52.9 |
| Gemini 3.1 Pro Preview | 52.6 |
| DeepSeek-V4-Pro | 51.6 |
| Qwen3.7-Plus | 49.3 |
| MiniMax M3 | 47.8 |
| GPT-5.4 Mini | 45.4 |
| GPT-5.4 Nano | 44.8 |
| Gemini 3.5 Flash-Lite | 43.2 |
| Inkling | 38.4 |
| Inkling-Small | 31.8 |
| Grok 4.3 | 18.4 |
| Gemini 3.1 Flash-Lite Preview | 8.6 |