Atlas

Benchmarks

← All benchmarks

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)

ModelScore
Claude Opus 570.0
Claude Fable 568.9
Opus 4.866.3
GPT-5.6 Terra63.1
GPT-5.6 Sol62.8
GPT-5.6 Luna60.5
Gemini 3.6 Flash59.4
Kimi K358.9
Gemini 3.5 Flash58.4
GPT-5.556.7
Sonnet 556.4
GLM-5.253.0
Kimi K2.649.7
Gemini 3.1 Pro Preview46.4
Muse Spark 1.146.3
DeepSeek-V4-Pro44.4
MiMo-V2.5-Pro43.6
Qwen3.7-Max43.5
Grok 4.541.5
GPT-5.4 Mini40.6
Sonnet 4.638.3
GPT-5.4 Nano37.5
Qwen3.7-Plus37.2
MiniMax M336.6
Gemini 3.5 Flash-Lite33.6
Inkling27.5
Inkling-Small24.3
Grok 4.311.4
Gemini 3.1 Flash-Lite Preview5.1
Loading Atlas data…