Excel Modeling Benchmark: leaderboard
Excel Modeling Benchmark is a text-and-spreadsheet benchmark for agents on Excel-based financial modeling tasks. The evaluated model works through Excel modeling problems, and the pinned metric is Score (%), measuring performance on those modeling tasks. Source: BenchmarkList’s attributed result table.
Metric: Score (%). Source: benchmarklist.com. Saturation forecast: Around February 2027. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 | 73.67 | #20 |
| 2 | Claude Opus 5 | 73.56 | #16 |
| 3 | GPT-5.6 Sol | 72.34 | #22 |
| 4 | Claude Opus 4.8 | 69.37 | #39 |
| 5 | GPT-5.6 Terra | 67.61 | #40 |
| 6 | GPT-5.6 Luna | 67.12 | #79 |
| 7 | Kimi K3 | 66.4 | #35 |
| 8 | Claude Sonnet 5 | 66.32 | #65 |
| 9 | Gemini 3.6 Flash | 65.41 | #57 |
| 10 | GPT-5.5 | 64.54 | #33 |
| 11 | Gemini 3.5 Flash | 63.55 | #66 |
| 12 | GLM-5.2 | 61.53 | #80 |
| 13 | Claude Sonnet 4.6 | 60.15 | #94 |
| 14 | Kimi K2.6 | 57.86 | #113 |
| 15 | Qwen 3.7 Max | 57.04 | #85 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=excel-modeling-benchmark · How It Works · Data refreshed daily, snapshot 2026-11-05.