---
title: "Excel Modeling Benchmark - Benchmark Evaluation - FinanceBenchmark"
description: "Evaluating agents on Excel-based financial modeling and spreadsheet valuation tasks (EMB v1.1)."
canonical: "https://financebenchmark.ai/benchmarks/emb"
type: "text/markdown"
---
# Excel Modeling Benchmark

> Evaluating agents on Excel-based financial modeling and spreadsheet valuation tasks (EMB v1.1).

## Table of Contents
- [1. Specifications & Metadata](#specifications)
- [2. Model Rankings on this Benchmark](#rankings)
- [3. Source Attribution & Citation](#attribution)

## 1. Specifications & Metadata {#specifications}

- **Slug:** `emb`
- **Domain Categories:** documentQA, forensic
- **Composite Weight:** 10 (Tier 3)
- **Task Count:** Variable
- **Source / Publisher:** VALS (2026)
- **GitHub Repository:** [https://www.vals.ai/benchmarks/emb](https://www.vals.ai/benchmarks/emb)

## 2. Model Rankings on this Benchmark {#rankings}

| Rank | Model | Organization | Overall | Eval Date | Source |
|:----:|:------|:-------------|:---:|:---------:|:------:|
| 1 | [Claude Fable 5.1](https://financebenchmark.ai/models/claude-fable-5-1.md) | Anthropic | **76.7** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 2 | [Claude Sonnet 5.5](https://financebenchmark.ai/models/claude-sonnet-5-5.md) | Anthropic | **75.9** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 3 | [Claude Opus 5.5](https://financebenchmark.ai/models/claude-opus-5-5.md) | Anthropic | **75.8** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 4 | [Gemini 4 Argon](https://financebenchmark.ai/models/gemini-4-argon.md) | Google | **74.8** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 5 | [Claude Fable 5](https://financebenchmark.ai/models/claude-fable-5.md) | Anthropic | **73.7** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 6 | [Claude Opus 5](https://financebenchmark.ai/models/claude-opus-5.md) | Anthropic | **73.6** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 7 | [Gemini 3.8 Flash](https://financebenchmark.ai/models/gemini-3-8-flash.md) | Google | **72.9** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 8 | [GPT-6 Astra](https://financebenchmark.ai/models/gpt-6-astra.md) | OpenAI | **72.7** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 9 | [GPT-5.6 Sol](https://financebenchmark.ai/models/gpt-5-6-sol.md) | OpenAI | **72.3** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 10 | [Gemini 3.7 Flash](https://financebenchmark.ai/models/gemini-3-7-flash.md) | Google | **71.3** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 11 | [Kimi K3](https://financebenchmark.ai/models/kimi-k3.md) | Moonshot AI | **71.3** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 12 | [GPT-6 Sol](https://financebenchmark.ai/models/gpt-6-sol.md) | OpenAI | **71.1** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 13 | [GPT-6 Luna](https://financebenchmark.ai/models/gpt-6-luna.md) | OpenAI | **70.0** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 14 | [DeepSeek V4.1 Flash](https://financebenchmark.ai/models/deepseek-v4-1-flash.md) | DeepSeek | **69.2** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 15 | [GLM 5.3](https://financebenchmark.ai/models/glm-5-3.md) | Zhipu AI | **69.1** | 2026-10 | [Ref](https://vals.ai/benchmarks/emb) |
| 16 | [Muse Spark 1.3 Max](https://financebenchmark.ai/models/muse-spark-1-3-max.md) | Meta | **67.4** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 17 | [GPT-5.6 Luna](https://financebenchmark.ai/models/gpt-5-6-luna.md) | OpenAI | **67.1** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 18 | [Claude Sonnet 5](https://financebenchmark.ai/models/claude-sonnet-5.md) | Anthropic | **66.3** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 19 | [GPT-5.6 Terra](https://financebenchmark.ai/models/gpt-5-6-terra.md) | OpenAI | **66.2** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 20 | [Gemini 3.6 Flash](https://financebenchmark.ai/models/gemini-3-6-flash.md) | Google | **65.4** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 21 | [GPT-5.5](https://financebenchmark.ai/models/gpt-5-5.md) | OpenAI | **64.5** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 22 | [Claude Opus 4.7](https://financebenchmark.ai/models/claude-opus-4-7.md) | Anthropic | **63.7** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 23 | [Grok 4.6](https://financebenchmark.ai/models/grok-4-6.md) | xAI | **62.7** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 24 | [Muse Spark 1.3](https://financebenchmark.ai/models/muse-spark-1-3.md) | Meta | **62.7** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 25 | [GLM 5.2](https://financebenchmark.ai/models/glm-5-2.md) | Zhipu AI | **61.5** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 26 | [Qwen 3.8 Max](https://financebenchmark.ai/models/qwen-3-8-max.md) | Alibaba | **60.1** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 27 | [Kimi K2.6](https://financebenchmark.ai/models/kimi-k2-6.md) | Moonshot AI | **57.9** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 28 | [DeepSeek V4 Flash](https://financebenchmark.ai/models/deepseek-v4-flash.md) | DeepSeek | **57.0** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 29 | [Muse Spark 1.2](https://financebenchmark.ai/models/muse-spark-1-2.md) | Meta | **57.0** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 30 | [Muse Spark 1.1](https://financebenchmark.ai/models/muse-spark-1-1.md) | Meta | **56.4** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 31 | [GLM 5.3 Flash](https://financebenchmark.ai/models/glm-5-3-flash.md) | Zhipu AI | **55.9** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 32 | [Grok 4.5](https://financebenchmark.ai/models/grok-4-5.md) | xAI | **52.9** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 33 | [DeepSeek V4 Pro (0813)](https://financebenchmark.ai/models/deepseek-v4-pro-0813.md) | DeepSeek | **52.8** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 34 | [Gemini 3.1 Pro](https://financebenchmark.ai/models/gemini-3-1-pro.md) | Google | **52.6** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 35 | [DeepSeek V4 Pro](https://financebenchmark.ai/models/deepseek-v4-pro.md) | DeepSeek | **51.6** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 36 | [Qwen 3.7 Plus](https://financebenchmark.ai/models/qwen-3-7-plus.md) | Alibaba | **49.4** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 37 | [MiniMax M3](https://financebenchmark.ai/models/minimax-m3.md) | MiniMax | **47.8** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 38 | [Gemini 3.5 Flash Lite](https://financebenchmark.ai/models/gemini-3-5-flash-lite.md) | Google | **43.2** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 39 | [Inkling](https://financebenchmark.ai/models/inkling.md) | Thinking Machines | **38.4** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 40 | [Inkling Small](https://financebenchmark.ai/models/inkling-small.md) | Thinking Machines | **31.8** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 41 | [Nemotron 3 Ultra](https://financebenchmark.ai/models/nemotron-3-ultra.md) | NVIDIA | **31.7** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 42 | [MiniMax M2.7](https://financebenchmark.ai/models/minimax-m2-7.md) | MiniMax | **28.4** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 43 | [Ling 3.0 Flash](https://financebenchmark.ai/models/ling-3-0-flash.md) | Ant Group | **25.0** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |
| 44 | [Grok 4.3](https://financebenchmark.ai/models/grok-4-3.md) | xAI | **18.4** | 2026-09 | [Ref](https://vals.ai/benchmarks/emb) |

## 3. Source Attribution & Citation {#attribution}

All scores for Excel Modeling Benchmark are derived directly from published literature or reproducible evaluation harnesses.
To submit updated evaluations, email [submit@financebenchmark.ai](mailto:submit@financebenchmark.ai).