Excel Modeling Benchmark

Key Takeaways

• Claude Opus 4.8 leads at 69.4%, ahead of Claude Sonnet 5 (66.3%) and GPT 5.5 (64.5%). With partial-credit grading, even top scores are substantial-but-incomplete financial models, not client-ready deliverables.
• Difficulty is consistent across models: nearly all score highest on Dataroom Summaries and lowest on LBO and DCF, the most deeply interdependent models, where early errors cascade.
• Numerical accuracy is the bottleneck: the leading model passes 87% of formula and 74% of presentation checks but only 61% of numerical checks.

Background

The Excel Modeling Benchmark (EMB) evaluates whether AI agents can generate complex Excel financial models typical in Investment Banking and Private Equity. Each task is focused on real-world utility: it provides a written prompt describing a business scenario along with a set of source files, and asks the agent to build the complete model, including the workbook’s tabs, structure, formulas, and formatting.

The benchmark tests the kind of modeling work that junior analysts do in practice. This includes forecasting how a company will perform, building out its financial statements, and working out what a company or a deal is worth. The core challenge is taking provided inputs (historical financials, customer database, company data provided in spreadsheets) and driving them through dozens of interdependent steps while keeping logic consistent end-to-end. Correct models should be usable in real-world scenarios. Most importantly, the produced models must open cleanly in Excel without issue. Circular references should be handled cleanly, case toggles should switch the entire model between scenarios (e.g. base/bull/bear) from a single input, and changing core inputs should propagate through the entire model. Each model is expected to take human experts a minimum of 5 hours of work to create from scratch.

The tasks span seven model categories: LBO Models, DCF Models, M&A Models, Operating Models, Comps Spreads, Dataroom Summaries, and a catch-all Misc Models category. All tasks, gold-standard models, and rubrics are authored and peer-reviewed by financial experts, drawing on realistic scenarios.

Each task is evaluated in two modes. In Template mode the agent fills in a provided workbook skeleton and is graded by exact cell match against the gold model. In Scratch mode it builds the workbook from nothing and is graded by a partial-credit rubric scoring three kinds of checks: 1) numerical (do values match the ground truth), 2) formula (are cells wired to the correct inputs), and 3) presentation (IB conventions like color-coding and number formats, plus source citations). EMB scores both correctness and usability, so layout and modeling conventions are just as important as the numbers and formulas.

Results

The Pareto chart above shows how accuracy trades off against cost and latency. Claude Opus 4.8 is the most accurate at 69.4%, at $12 per task, while Claude Sonnet 5 ranks second at 66.3% but is the most expensive model of all at $15.44 per task. Both cost several times more than GPT 5.5, which reaches 64.5% at a fraction of the cost. Among the leading models, Kimi K2.6 is the most cost-efficient, holding 58% accuracy at just $2.20 per task, and MiMo V2.5 Pro is cheaper still at $0.22 while staying above 50%.

Per-category performance is consistent across evaluated agents, with nearly all performing strongest on Dataroom Summaries and weakest on LBO and DCF models. LBO and DCF are one long chain of linked calculations, so errors propagate throughout the model; Dataroom Summaries lean more on summarizing provided data, so errors stay localized.