---
title: "Claude Sonnet 5.5 (Anthropic) - Financial AI Performance - FinanceBenchmark"
description: "Independent evaluation and benchmark scores for Claude Sonnet 5.5 on financial reasoning."
canonical: "https://financebenchmark.ai/models/claude-sonnet-5-5"
type: "text/markdown"
---
# Claude Sonnet 5.5

> Developed by **Anthropic** · Released 2026-09-18 · License: proprietary

## Table of Contents
- [1. Model Profile & Summary](#profile)
- [2. FB Composite Score](#composite-score)
- [3. All Evaluated Benchmarks](#benchmarks)
- [4. Certification & Verification](#verification)

## 1. Model Profile & Summary {#profile}

- **Organization:** Anthropic
- **Release Date:** 2026-09-18
- **License:** proprietary (Proprietary API)
- **Context Window:** 1M
- **FB Certified:** Standard Attribution

## 2. FB Composite Score {#composite-score}

**Composite FB Score: 58.4 / 100**

- Benchmarks Evaluated: **3 of 42**

## 3. All Evaluated Benchmarks {#benchmarks}

| Benchmark | Category | Overall Score | Eval Date | Source |
|:----------|:---------|:-------------:|:---------:|:------:|
| [Excel Modeling Benchmark](https://financebenchmark.ai/benchmarks/emb.md) | documentQA, forensic | **75.9%** | 2026-10 | [Paper](https://vals.ai/benchmarks/emb) |
| [Finance Agent Benchmark](https://financebenchmark.ai/benchmarks/finance-agent.md) | agentTasks | **58.1%** | 2026-10 | [Paper](https://vals.ai/benchmarks/fabv2) |
| [Tax Agent Bench](https://financebenchmark.ai/benchmarks/tax-agent-bench.md) | forensic, agentTasks | **42.0%** | 2026-10 | [Paper](https://vals.ai/benchmarks/tax_agent_bench) |

## 4. Certification & Verification {#verification}

Embed live verification badge:

```html
<img src="https://financebenchmark.ai/embed/badge/claude-sonnet-5-5" alt="Claude Sonnet 5.5 FinanceBenchmark Score" />
```