# Vals Finance Index v1 (Vals Finance Index)

> Vals AI composite of agentic finance work: analyst research on company filings, financial modeling in Excel and corporate tax research, weighted by each sub-sector's share of U.S. GDP.

Canonical page: https://benchlm.ai/benchmarks/vals-finance-index

- Category: [Agentic](/agentic)
- Last updated: October 27, 2026

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

## About Vals Finance Index

- Year: 2026
- Tasks: 3 finance benchmarks
- Format: GDP-weighted accuracy across three benchmarks
- Difficulty: Agentic analyst research, Excel financial modeling and corporate tax research
- Paper: [Vals Finance Index leaderboard and methodology](https://www.vals.ai/benchmarks/finance_index)

Vals released v1 on October 21, 2026. Finance Agent v2.1 and the Excel Modeling Benchmark v1.1 average into a securities and investments score (weight 1.6) and Tax Agent Bench is the tax score (weight 0.5), combined as (1.6 x securities + 0.5 x tax) / 2.1. Weights come from Bureau of Economic Analysis value added as a share of U.S. GDP. We mirror the published aggregates as a display-only composite, outside overall and category rankings.

Vals Finance Index is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (33 models)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Gemini 4 Carbon](/models/gemini-4-carbon) | high reasoning | Google | 66.35% |
| 2 | [Claude Opus 5.5](/models/claude-opus-5-5) | — | Anthropic | 65.59% |
| 3 | [Gemini 4 Argon](/models/gemini-4-argon) | high reasoning | Google | 64.89% |
| 4 | [Muse Wonder Full](/models/muse-wonder-full) | max reasoning | Meta | 64.55% |
| 5 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | — | Anthropic | 64.53% |
| 6 | [Qwen3.8 Max Internal](https://www.vals.ai/models/alibaba_qwen3.8-max-internal) | — | Alibaba | 61.66% |
| 7 | [Muse Wonder](/models/muse-wonder) | max reasoning | Meta | 61.23% |
| 8 | [DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash) | max reasoning | DeepSeek | 60.89% |
| 9 | [GLM-5.3](/models/glm-5-3) | max reasoning | Z.AI | 60.54% |
| 10 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | high reasoning | Google | 60.46% |
| 11 | [Grok 4.7](/models/grok-4-7) | xhigh reasoning | xAI | 58.46% |
| 12 | [Kimi K3](/models/kimi-k3) | max reasoning | Moonshot AI | 57.95% |
| 13 | [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) | — | Xiaomi | 57.85% |
| 14 | [Hy4 preview](/models/hy4-preview) | — | Tencent | 57.51% |
| 15 | [Claude Haiku 5.5](/models/claude-haiku-5-5) | — | Anthropic | 57.45% |
| 16 | [MiMo-V2.6-Flash](/models/mimo-v2-6-flash) | — | Xiaomi | 57.15% |
| 17 | [DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash) | max reasoning | DeepSeek | 57.08% |
| 18 | [Mistral Large 4](/models/mistral-large-4) | high reasoning | Mistral | 56.90% |
| 19 | [Kimi K3.1 Pro](/models/kimi-3-1-pro) | max reasoning | Moonshot AI | 56.01% |
| 20 | [MiniMax M3.1 Flash](/models/minimax-m3-1-flash) | — | MiniMax | 55.91% |
| 21 | [GLM-5.3-Flash](/models/glm-5-3-flash) | max reasoning | Z.AI | 55.83% |
| 22 | [GPT-6.1 Sol](/models/gpt-6-1-sol) | max reasoning | OpenAI | 55.81% |
| 23 | [GPT-6 Astra](/models/gpt-6-astra) | max reasoning | OpenAI | 55.64% |
| 24 | [Step 5 Preview](/models/step-5-preview) | — | StepFun | 55.43% |
| 25 | [GPT-6 Luna](/models/gpt-6-luna) | max reasoning | OpenAI | 53.05% |
| 26 | [Muse Spark Open](/models/muse-spark-open) | xhigh reasoning | Meta | 52.99% |
| 27 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | max reasoning | DeepSeek | 52.94% |
| 28 | [GPT-6.1 Terra](/models/gpt-6-1-terra) | max reasoning | OpenAI | 52.86% |
| 29 | [MiniMax M3](/models/minimax-m3) | — | MiniMax | 48.37% |
| 30 | [Mercury 3](/models/mercury-3) | high reasoning | Inception | 47.22% |
| 31 | [Beam 1.0](https://www.vals.ai/models/reflection_Beam-1.0) | — | Reflection | 46.50% |
| 32 | [Inkling](/models/inkling) | 0.99 reasoning | Thinking Machines Lab | 38.25% |
| 33 | [Inkling-Small](/models/inkling-small) | 0.99 reasoning | Thinking Machines Lab | 36.27% |

## FAQ

### What does Vals Finance Index measure?

Vals AI composite of agentic finance work: analyst research on company filings, financial modeling in Excel and corporate tax research, weighted by each sub-sector's share of U.S. GDP.

### Which model leads the published Vals Finance Index snapshot?

Gemini 4 Carbon currently leads the published Vals Finance Index snapshot with a score of 66.35%.

### How many models are evaluated on Vals Finance Index?

The October 27, 2026 contains 33 AI models.

### Does Vals Finance Index affect BenchLM's overall score?

Not directly. Vals Finance Index is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.