Excel Modeling Benchmark DCF
Professional Work · 2026-07-01
This row reports the category score for discounted-cash-flow tasks in Excel Modeling Benchmark.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 70.0 |
| Claude Fable 5 | 68.9 |
| Opus 4.8 | 66.3 |
| GPT-5.6 Terra | 63.1 |
| GPT-5.6 Sol | 62.8 |
| GPT-5.6 Luna | 60.5 |
| Gemini 3.6 Flash | 59.4 |
| Kimi K3 | 58.9 |
| Gemini 3.5 Flash | 58.4 |
| GPT-5.5 | 56.7 |
| Sonnet 5 | 56.4 |
| GLM-5.2 | 53.0 |
| Kimi K2.6 | 49.7 |
| Gemini 3.1 Pro Preview | 46.4 |
| Muse Spark 1.1 | 46.3 |
| DeepSeek-V4-Pro | 44.4 |
| MiMo-V2.5-Pro | 43.6 |
| Qwen3.7-Max | 43.5 |
| Grok 4.5 | 41.5 |
| GPT-5.4 Mini | 40.6 |
| Sonnet 4.6 | 38.3 |
| GPT-5.4 Nano | 37.5 |
| Qwen3.7-Plus | 37.2 |
| MiniMax M3 | 36.6 |
| Gemini 3.5 Flash-Lite | 33.6 |
| Inkling | 27.5 |
| Inkling-Small | 24.3 |
| Grok 4.3 | 11.4 |
| Gemini 3.1 Flash-Lite Preview | 5.1 |