Excel Modeling Benchmark v1.1 DCF
Professional Work · 2026-10-19
Category score for discounted-cash-flow tasks in Excel Modeling Benchmark v1.1.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Sonnet 5.5 | 73.0 |
| Claude Fable 5.1 | 71.5 |
| Claude Opus 5.5 | 69.9 |
| GPT-6.1 Sol | 67.1 |
| Gemini 3.8 Flash | 66.1 |
| GPT-6 Astra | 66.0 |
| Step 5 Preview | 65.8 |
| Muse Wonder Full | 65.7 |
| Gemini 4 Argon | 65.5 |
| GLM-5.3 Flash | 65.3 |
| Grok 4.7 | 65.1 |
| GPT-6 Luna | 64.8 |
| MiMo-V2.6-Pro | 64.8 |
| Kimi K3 | 64.4 |
| GLM-5.3 | 63.7 |
| Muse Wonder | 63.7 |
| Claude Haiku 5.5 | 63.1 |
| MiMo-V2.6-Flash | 61.6 |
| Mistral Large 4 Preview | 60.9 |
| Hy4 Preview | 60.0 |
| DeepSeek V4.1 Flash | 59.9 |
| DeepSeek V4.1 Flash 1017 | 59.7 |
| MiniMax M3.1 Flash | 58.7 |
| DeepSeek V4 Pro 0813 | 58.1 |
| Qwen3.8-Max | 54.2 |
| Beam 1.0 501B A23B | 53.9 |
| MiniMax M3 | 52.9 |
| Muse Spark Open | 49.9 |
| Mercury 3 | 41.4 |
| Inkling-Small | 34.7 |
| Inkling | 27.4 |