# Best AI model for finance and accounting — November 2026

> Best AI model for finance and accounting (November 2026): on Vals Finance Index, run by Vals AI, Gemini 4 Carbon, Gemini 4 Hydrogen and Gemini 4 Argon are within 1.5 points of each other. Evidence, constraints, and caveats included.

## Constraints on this page

A builder choosing by accuracy, hosted processing allowed, any price, ordinary input size. Every refine link below changes one answer.

## The shortlist for finance and accounting

| # | Model | Creator | Vals Finance Index | Why |
|---|---|---|---|---|
| 1 | [Gemini 4 Carbon](/models/gemini-4-carbon) | Google | 67.0% | Highest Vals Finance Index result, with 2 other models within 1.5 points; $4.00 for the stated workload; 1M context |
| 2 | [Gemini 4 Hydrogen](/models/gemini-4-hydrogen) | Google | 66.1% | 66.1% on Vals Finance Index, run by Vals AI; $3.00 for the stated workload; 1M context |
| 3 | [Gemini 4 Argon](/models/gemini-4-argon) | Google | 66.0% | 66.0% on Vals Finance Index, run by Vals AI; $4.00 for the stated workload; 1M context |
| 4 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 65.3% | 65.3% on Vals Finance Index, run by Vals AI; $8.00 for the stated workload; 1M context |
| 5 | [Muse Wonder Full](/models/muse-wonder-full) | Meta | 64.6% | 64.6% on Vals Finance Index, run by Vals AI; 1M context |

Ordered by Vals Finance Index result under the stated constraints.

Tested settings: Gemini 4 Carbon as Gemini 4 Carbon (high effort); Gemini 4 Hydrogen as Gemini 4 Hydrogen (xhigh effort); Gemini 4 Argon as Gemini 4 Argon (high effort); Claude Opus 5.5 as Claude Opus 5.5 (max effort); Muse Wonder Full as Muse Wonder Full (max effort).

## The top ten for finance and accounting, with API prices

The first ten models on the same evidence and constraints as the shortlist, with each provider's API price in US dollars per million tokens. Inkling 2 Small costs the least of the ten for a workload of 1M input and 200k output tokens: $0.30 per million input tokens and $1.00 per million output tokens. Two of the ten have no API price on file.

| # | Model | Creator | Vals Finance Index | Input | Output |
|---|---|---|---|---|---|
| 1 | [Gemini 4 Carbon](/models/gemini-4-carbon) | Google | 67.0% | $2.00 | $10.00 |
| 2 | [Gemini 4 Hydrogen](/models/gemini-4-hydrogen) | Google | 66.1% | $1.50 | $7.50 |
| 3 | [Gemini 4 Argon](/models/gemini-4-argon) | Google | 66.0% | $2.00 | $10.00 |
| 4 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 65.3% | $4.00 | $20.00 |
| 5 | [Muse Wonder Full](/models/muse-wonder-full) | Meta | 64.6% | No API price on file |  |
| 6 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | 64.5% | $2.00 | $10.00 |
| 7 | [Claude Fable 5.2](/models/claude-fable-5-2) | Anthropic | 63.6% | $8.00 | $40.00 |
| 8 | [Inkling 2 Small](/models/inkling-2-small) | Thinking Machines Lab | 61.5% | $0.30 | $1.00 |
| 9 | [GLM-5.3](/models/glm-5-3) | Z.AI | 61.4% | No API price on file |  |
| 10 | [Muse Wonder](/models/muse-wonder) | Meta | 61.2% | $4.00 | $20.00 |

Prices are list API rates before caching, batch discounts and special tiers. See [API pricing for every model](/llm-pricing).

## ChatGPT, Claude, Gemini, or Copilot?

Of the three apps whose models we can score, Gemini has the highest result here: Gemini 4 Carbon scores 67.0% on Vals Finance Index.

- ChatGPT: [GPT-6.1 Sol](/models/gpt-6-1-sol), 55.8%. Plan nearest $20: Plus, $20 a month, which lists: GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol and GPT-6 Luna in Codex; GPT-6.1 Sol is available in Work and Codex, not Chat.
- Claude: [Claude Opus 5.5](/models/claude-opus-5-5), 65.3%. Plan nearest $20: Pro, $20 a month, which lists: Opus, Sonnet and Haiku; Fable is listed under usage credits rather than the included allowance.
- Gemini: [Gemini 4 Carbon](/models/gemini-4-carbon), 67.0% (highest of the three). Plan nearest $20: Google AI Pro, $19.99 a month, which lists: Gemini 4 Argon, the Pro model and the Flash model.
- Microsoft Copilot: not scored. Microsoft doesn’t name the model Copilot runs, so no benchmark result can be attached to it. Plan nearest $20: Microsoft 365 Premium, $19.99 a month. [How it compares on plans and data terms](/compare/chatgpt-vs-copilot)

Each entry is the highest-scoring model that company sells, not the model your plan opens by default, so check what the plan lists before you pay. The plan shown is each app’s plan nearest $20, read October 16, 2026 for ChatGPT, November 10, 2026 for Copilot, and November 11, 2026 for Claude and Gemini.

Compare the apps: [ChatGPT vs Claude](/compare/chatgpt-vs-claude), [ChatGPT vs Gemini](/compare/chatgpt-vs-gemini), [Claude vs Gemini](/compare/claude-vs-gemini), [ChatGPT vs Copilot](/compare/chatgpt-vs-copilot).

## Before your company approves a model

The shortlist ranks models. Whether you can use one at work depends on the provider: whether it trains on what you send, how long it keeps it, and what it will sign. The table covers the providers behind the models above, plus OpenAI, and the two clouds that sell many of the same models under their own terms. Each cell is what the provider’s own pages said on November 10, 2026. With ledgers, payroll, or client tax files, we’d read the retention and SOC 2 columns first.

| Provider | Trains on your inputs? | Inputs kept | SOC 2 report | HIPAA | Single sign-on |
|---|---|---|---|---|---|
| Google (Gemini API, Gemini on Google Cloud, and Gemini in Google Workspace) | Not on paid plans | No number given | Type II | BAA: Cloud and Workspace | Through Workspace |
| Anthropic (Claude API, Claude Team, and Claude Enterprise) | No, by default | 30 days, with exceptions | Type II | BAA: API and Enterprise | Team and Enterprise |
| OpenAI (OpenAI API, ChatGPT Business, and ChatGPT Enterprise) | No, by default | 30 days; state until deleted | Type 2 | BAA on request, API | Business, Enterprise, Edu |
| Microsoft Foundry (Azure) (Models sold by Azure, including OpenAI, xAI, Meta, Mistral, and DeepSeek models) | No | Flagged prompts may be kept | Type 2 | BAA, in-scope services | Microsoft Entra ID |
| Amazon Bedrock (Models from Anthropic, OpenAI, Meta, Mistral, xAI, DeepSeek, Moonshot AI, Qwen, Z.AI, and others) | No | No period given | In audit scope | Eligible, with a BAA | IAM Identity Center |

“Not stated” means the pages we read don’t say. It doesn’t mean the provider lacks it. Each row covers the plans named under the provider. A personal plan has its own terms, and your signed agreement overrides the public page. Meta: We found no page that sets out business data terms for Meta’s Model API. Its models are also sold on Microsoft Foundry (Azure), Amazon Bedrock, and Google Cloud (preview), where that cloud’s terms apply. Z.AI: Z.AI’s developer privacy policy does not say plainly whether API inputs are used for training. Its models are also sold on Amazon Bedrock and Google Cloud, where that cloud’s terms apply. We haven’t read the terms for Thinking Machines Lab yet.

[Every answer in full, with its source](/hipaa-compliant-ai).

## What this shortlist rests on

One benchmark: Vals Finance Index. Agent work a finance team does: analyst research on company filings, building financial models in Excel, and corporate tax research. Vals AI combines the three into one index. A result a model's own provider ran is left out, and a model nobody has run there is not listed.

- [Vals Finance Index](/benchmarks/vals-finance-index) · sets the order · run by Vals AI · 36 models have a published result
- [APEX-Accounting (Mercor)](/benchmarks/mercorapexaccounting) · related evidence, not used for the order. Month-end close tasks across files and applications, run by Mercor on a few agent setups.
- [TaxEval v2](/benchmarks/taxevalv2) · related evidence, not used for the order. Tax questions answered without tools, also run by Vals AI on more models.
- [CorpFin v2](/benchmarks/valscorpfinv2) · related evidence, not used for the order. Questions over long credit agreements, also run by Vals AI.

## What to verify before choosing

- A benchmark result is not an accounting or tax qualification. Figures, filings and advice need review by a qualified person, and the index tests none of your own ledgers or software.
- Ranked on one benchmark: Vals Finance Index, run by Vals AI. 36 models have a published result; a model without one is not listed.

## Refine

- [Change any answer in the selector](/tools/llm-selector?audience=builders&family=documents&useCase=finance&priority=accuracy&privacy=hosted&budget=any&context=normal)
- [Must run on my own hardware](/tools/llm-selector?audience=builders&family=documents&useCase=finance&priority=accuracy&privacy=local&context=normal)
- [Cost matters most](/tools/llm-selector?audience=builders&family=documents&useCase=finance&priority=cost&privacy=hosted&budget=any&context=normal)
- [Speed matters most](/tools/llm-selector?audience=builders&family=documents&useCase=finance&priority=speed&privacy=hosted&budget=any&context=normal)
- [Long documents or a large codebase](/tools/llm-selector?audience=builders&family=documents&useCase=finance&priority=accuracy&privacy=hosted&budget=any&context=large)
- [Choosing an everyday assistant, not an API](/tools/llm-selector?audience=everyday&family=documents&useCase=finance&priority=accuracy&privacy=hosted&budget=any&context=normal)
- [Describe your own job instead](/tools/llm-selector)

## Questions

**Which AI model is best for finance and accounting?**

No single model is clearly best for finance and accounting on BenchLM's evidence. On Vals Finance Index, run by Vals AI, Gemini 4 Carbon (67.0%), Gemini 4 Hydrogen (66.1%) and Gemini 4 Argon (66.0%) are within 1.5 points of each other. A benchmark result is not an accounting or tax qualification. Figures, filings and advice need review by a qualified person, and the index tests none of your own ledgers or software.

**Which models come next for finance and accounting?**

Claude Opus 5.5 (65.3%), Muse Wonder Full (64.6%) follow on the same benchmark. Compare the leaders on three representative examples of your own work.

**How does BenchLM pick the best ai model for finance and accounting?**

The page runs the LLM Selector with fixed answers: a builder choosing by accuracy, hosted processing allowed, any price, ordinary input size. The selector uses Vals Finance Index, one benchmark run by Vals AI on every listed model, filters by the stated constraints, and orders by that evidence. It never adds a hidden fit score or a bonus for open weights or reasoning style.

**Why does this page use Vals Finance Index and not a general score?**

A general score answers several jobs at once. Vals Finance Index is closer to this job. Agent work a finance team does: analyst research on company filings, building financial models in Excel, and corporate tax research. Vals AI combines the three into one index. Only results Vals AI published itself are used, so a model nobody has run there is not listed. 36 models have a result.

**What do the top models for finance and accounting cost?**

Among the ten highest-ranked models on this page, Inkling 2 Small costs the least for a workload of 1M input and 200k output tokens: $0.30 per million input tokens and $1.00 per million output tokens. Claude Fable 5.2 costs the most, at $8.00 and $40.00. These are API rates in the November 13, 2026 data. Assistant subscriptions are priced separately.

**Can I change the constraints?**

Yes. Every link under "Refine" opens the selector with one answer changed, and the address carries the answers so a result can be shared or reopened against the current dataset.

Data updated 2026-11-13. Method: bench-align-v5.8-2026-09-30.

Canonical page: https://benchlm.ai/best/for/finance