# Vals AI Financial Coaching Bench (Financial Coaching Bench)

> Can AI coach a household through a real financial problem?

Canonical page: https://benchlm.ai/benchmarks/financial-coaching-bench

- Category: [Agentic](/agentic)
- Last updated: November 13, 2026

Evaluation results published by [Vals AI](https://www.vals.ai/benchmarks/financial-coaching-bench). Published leaderboard aggregates and evaluation settings only. Dataset contents are not included.

## About Financial Coaching Bench

- Year: 2026
- Tasks: 256 simulated coaching conversations across 7 financial areas
- Format: Share of practitioner checklist items met
- Difficulty: Household financial coaching with follow-up questions
- Paper: [Financial Coaching Bench leaderboard and methodology](https://www.vals.ai/benchmarks/financial-coaching-bench)

Vals published Financial Coaching Bench on November 13, 2026. Each of 256 scored scenarios gives the model a client's opening message about a money problem, such as a collections notice, a rent increase or a defaulted loan. A simulated client answers the coach's questions from a hidden fact sheet of income, debts, deadlines, savings and household. The coach can search the web and ends by delivering a plan. Practitioners wrote a checklist of what a good coach recommends, warns about or gets right, and the score is the share of checklist items met. BenchLM mirrors the published aggregates as display-only external evidence, outside overall and category rankings.

Financial Coaching Bench is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (28 models)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Claude Opus 5.5](/models/claude-opus-5-5) | — | Anthropic | 76.16% |
| 2 | [Muse Spark 1.2](/models/muse-spark-1-2) | xhigh reasoning | Meta | 75.74% |
| 3 | [Claude Fable 5.1](/models/claude-fable-5-1) | — | Anthropic | 75.71% |
| 4 | [Qwen3.8 Max](/models/qwen3-8-max) | — | Alibaba | 75.58% |
| 5 | [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) | — | Xiaomi | 75.37% |
| 6 | [Muse Wonder Full](/models/muse-wonder-full) | max reasoning | Meta | 74.96% |
| 7 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | — | Anthropic | 74.94% |
| 8 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | max reasoning | OpenAI | 74.89% |
| 9 | [Kimi K3](/models/kimi-k3) | max reasoning | Moonshot AI | 74.53% |
| 10 | [Grok 4.7](/models/grok-4-7) | xhigh reasoning | xAI | 74.07% |
| 11 | [GLM-5.3](/models/glm-5-3) | max reasoning | Z.AI | 74.06% |
| 12 | [Muse Wonder](/models/muse-wonder) | max reasoning | Meta | 73.78% |
| 13 | [Gemini 4 Argon](/models/gemini-4-argon) | high reasoning | Google | 73.13% |
| 14 | [DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash) | high reasoning | DeepSeek | 72.83% |
| 15 | [Muse Spark 1.3](/models/muse-spark-1-3) | xhigh reasoning | Meta | 70.99% |
| 16 | [GPT-5.6 Terra](/models/gpt-5-6-terra) | max reasoning | OpenAI | 70.98% |
| 17 | [Muse Spark 1.3 Max](https://www.vals.ai/models/meta_muse_spark_1_3_max) | max reasoning | Meta | 70.29% |
| 18 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | max reasoning | OpenAI | 69.29% |
| 19 | [MiniMax M3](/models/minimax-m3) | — | MiniMax | 69.05% |
| 20 | [GPT-6.1 Sol](/models/gpt-6-1-sol) | max reasoning | OpenAI | 68.55% |
| 21 | [GPT-6 Astra](/models/gpt-6-astra) | max reasoning | OpenAI | 67.53% |
| 22 | [Gemini 3.1 Pro Preview](https://www.vals.ai/models/google_gemini-3.1-pro-preview) | high reasoning | Google | 66.73% |
| 23 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | high reasoning | Google | 66.27% |
| 24 | [Gemini 3.6 Flash](/models/gemini-3-6-flash) | high reasoning | Google | 65.76% |
| 25 | [GPT-6 Luna](/models/gpt-6-luna) | max reasoning | OpenAI | 65.24% |
| 26 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | high reasoning | Google | 62.96% |
| 27 | [GPT-6 Sol](/models/gpt-6-sol) | max reasoning | OpenAI | 62.61% |
| 28 | [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | high reasoning | Google | 57.47% |

## FAQ

### What does Financial Coaching Bench measure?

Can AI coach a household through a real financial problem?

### Which model leads the published Financial Coaching Bench snapshot?

Claude Opus 5.5 currently leads the published Financial Coaching Bench snapshot with a score of 76.16%.

### How many models are evaluated on Financial Coaching Bench?

The November 13, 2026 contains 28 AI models.

### Does Financial Coaching Bench affect BenchLM's overall score?

Not directly. Financial Coaching Bench is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.