---
title: "GPT-5.6 Terra (OpenAI) - Financial AI Performance - FinanceBenchmark"
description: "Independent evaluation and benchmark scores for GPT-5.6 Terra on financial reasoning."
canonical: "https://financebenchmark.ai/models/gpt-5-6-terra"
type: "text/markdown"
---
# GPT-5.6 Terra

> Developed by **OpenAI** · Released 2026-07-09 · 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:** OpenAI
- **Release Date:** 2026-07-09
- **License:** proprietary (Proprietary API)
- **Context Window:** 1M
- **FB Certified:** Standard Attribution

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

**Composite FB Score: 63.1 / 100**

- Benchmarks Evaluated: **25 of 42**

## 3. All Evaluated Benchmarks {#benchmarks}

| Benchmark | Category | Overall Score | Eval Date | Source |
|:----------|:---------|:-------------:|:---------:|:------:|
| [VALS Index](https://financebenchmark.ai/benchmarks/vals-index.md) | verification, numerical, agentTasks | **56.5%** | 2026-07 | [Paper](https://vals.ai) |
| [Code Migration](https://financebenchmark.ai/benchmarks/code-migration.md) | agentTasks | **36.5%** | 2026-07 | [Paper](https://vals.ai) |
| [Excel Modeling Benchmark](https://financebenchmark.ai/benchmarks/emb.md) | documentQA, forensic | **66.2%** | 2026-09 | [Paper](https://vals.ai/benchmarks/emb) |
| [Finance Agent Benchmark](https://financebenchmark.ai/benchmarks/finance-agent.md) | agentTasks | **54.4%** | 2026-09 | [Paper](https://vals.ai/benchmarks/fabv2) |
| [Legal Research Bench](https://financebenchmark.ai/benchmarks/legal-research-bench.md) | documentQA, forensic | **40.9%** | 2026-07 | [Paper](https://vals.ai) |
| [MedCode](https://financebenchmark.ai/benchmarks/medcode.md) | verification | **43.4%** | 2026-07 | [Paper](https://vals.ai) |
| [MedScribe](https://financebenchmark.ai/benchmarks/medscribe.md) | documentQA | **82.9%** | 2026-07 | [Paper](https://vals.ai) |
| [MortgageTax Benchmark](https://financebenchmark.ai/benchmarks/mortgagetax.md) | numerical, forensic | **67.3%** | 2026-07 | [Paper](https://vals.ai) |
| [ProofBench v1.1](https://financebenchmark.ai/benchmarks/proofbench-v1-1.md) | numerical, verification | **71.0%** | 2026-07 | [Paper](https://vals.ai) |
| [SAGE](https://financebenchmark.ai/benchmarks/sage.md) | agentTasks | **47.0%** | 2026-07 | [Paper](https://vals.ai) |
| [Public Benefits Bench](https://financebenchmark.ai/benchmarks/public-benefits-bench.md) | verification, forensic | **62.4%** | 2026-07 | [Paper](https://vals.ai) |
| [TaxEval v2](https://financebenchmark.ai/benchmarks/taxeval-v2.md) | verification, forensic | **76.2%** | 2026-09 | [Paper](https://vals.ai/benchmarks/taxeval_v2) |
| [Vibe Code Bench v1.1](https://financebenchmark.ai/benchmarks/vibe-code-bench-v1-1.md) | agentTasks | **67.8%** | 2026-07 | [Paper](https://vals.ai) |
| [Harvey's Legal Agent](https://financebenchmark.ai/benchmarks/harveys-legal-agent.md) | agentTasks, forensic | **0.4%** | 2026-07 | [Paper](https://vals.ai) |
| [GPQA Diamond](https://financebenchmark.ai/benchmarks/gpqa-diamond.md) | numerical, verification | **90.9%** | 2026-07 | [Paper](https://vals.ai) |
| [IOI](https://financebenchmark.ai/benchmarks/ioi.md) | numerical | **65.3%** | 2026-07 | [Paper](https://vals.ai) |
| [LiveCodeBench](https://financebenchmark.ai/benchmarks/livecodebench.md) | agentTasks | **85.9%** | 2026-07 | [Paper](https://vals.ai) |
| [LegalBench](https://financebenchmark.ai/benchmarks/legalbench.md) | documentQA, forensic | **85.1%** | 2026-07 | [Paper](https://vals.ai) |
| [MMLU Pro](https://financebenchmark.ai/benchmarks/mmlu-pro.md) | numerical, verification | **86.7%** | 2026-07 | [Paper](https://vals.ai) |
| [MMMU](https://financebenchmark.ai/benchmarks/mmmu.md) | documentQA, numerical | **86.5%** | 2026-07 | [Paper](https://vals.ai) |
| [ProgramBench](https://financebenchmark.ai/benchmarks/programbench.md) | agentTasks | **0.5%** | 2026-07 | [Paper](https://vals.ai) |
| [SkillsBench](https://financebenchmark.ai/benchmarks/skillsbench.md) | agentTasks | **60.6%** | 2026-07 | [Paper](https://vals.ai) |
| [SWE-bench](https://financebenchmark.ai/benchmarks/swe-bench.md) | agentTasks | **75.2%** | 2026-07 | [Paper](https://vals.ai) |
| [Terminal-Bench 2.1](https://financebenchmark.ai/benchmarks/terminal-bench-2-1.md) | agentTasks | **73.4%** | 2026-07 | [Paper](https://vals.ai) |
| [Tax Agent Bench](https://financebenchmark.ai/benchmarks/tax-agent-bench.md) | forensic, agentTasks | **65.2%** | 2026-09 | [Paper](https://vals.ai/benchmarks/tax_agent_bench) |

## 4. Certification & Verification {#verification}

Embed live verification badge:

```html
<img src="https://financebenchmark.ai/embed/badge/gpt-5-6-terra" alt="GPT-5.6 Terra FinanceBenchmark Score" />
```