Atlas

Benchmarks

← All benchmarks

Excel Modeling Benchmark Operating

Professional Work · 2026-07-01

This row reports the category score for operating-model tasks in Excel Modeling Benchmark.

Top models (higher is better)

ModelScore
Claude Opus 573.5
Claude Fable 572.8
GPT-5.6 Luna72.7
GPT-5.6 Sol67.3
Opus 4.866.7
Sonnet 565.5
GPT-5.564.5
Gemini 3.6 Flash63.0
GLM-5.262.9
Grok 4.561.9
GPT-5.6 Terra60.4
Kimi K359.4
Gemini 3.5 Flash58.7
Gemini 3.1 Pro Preview58.1
Sonnet 4.658.1
Qwen3.7-Plus58.0
Muse Spark 1.157.6
Kimi K2.656.9
MiMo-V2.5-Pro55.2
Qwen3.7-Max52.1
GPT-5.4 Mini50.8
MiniMax M348.9
DeepSeek-V4-Pro47.2
Inkling41.6
GPT-5.4 Nano36.7
Inkling-Small36.4
Gemini 3.5 Flash-Lite32.7
Grok 4.316.3
Gemini 3.1 Flash-Lite Preview5.4
Loading Atlas data…