# Vals Finance Agent v1.1 (Finance Agent v1.1)

> An archived Vals benchmark covering retrieval, numerical reasoning, financial modeling, market analysis, earnings, trends, and adjustments.

Canonical page: https://benchlm.ai/benchmarks/valsfinanceagentv1

- Category: [Agentic](/agentic)
- Last updated: June 4, 2026

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

## About Finance Agent v1.1

- Year: 2026
- Tasks: 11 financial analyst task views
- Format: Accuracy with task-level breakdowns
- Difficulty: Professional financial analysis
- Paper: [Finance Agent v1.1](https://www.vals.ai/benchmarks/finance_agent)

We mirror all 51 published rows and 11 task views for historical comparison. Finance Agent v2 is the current Vals benchmark, so v1.1 stays display only and does not enter weighted rankings.

Finance Agent v1.1 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (51 models)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Claude Opus 4.7](/models/claude-opus-4-7) | — | Anthropic | 64.37% |
| 2 | [Claude Sonnet 4.6](/models/claude-sonnet-4-6) | — | Anthropic | 63.33% |
| 3 | [Muse Spark](/models/muse-spark) | — | Meta | 60.59% |
| 4 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | max reasoning | DeepSeek | 60.39% |
| 5 | [Claude Opus 4.6 (Adaptive)](/models/claude-opus-4-6-thinking) | — | Anthropic | 60.05% |
| 6 | [GPT-5.5](/models/gpt-5-5) | xhigh reasoning | OpenAI | 59.96% |
| 7 | [Gemini 3.1 Pro Preview](https://www.vals.ai/models/google_gemini-3.1-pro-preview) | high reasoning | Google | 59.72% |
| 8 | [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking) | — | Anthropic | 58.81% |
| 9 | [GPT-5.2](/models/gpt-5-2) | xhigh reasoning | OpenAI | 58.53% |
| 10 | [GLM-5.1](/models/glm-5-1) | — | Z.AI | 57.66% |
| 11 | [GPT-5.4](/models/gpt-5-4) | xhigh reasoning | OpenAI | 57.15% |
| 12 | [Kimi K2.6](/models/kimi-2-6) | — | Moonshot AI | 57.06% |
| 13 | [GPT-5.1](/models/gpt-5-1) | high reasoning | OpenAI | 55.31% |
| 14 | [Gemini 3 Pro Preview](https://www.vals.ai/models/google_gemini-3-pro-preview) | high reasoning | Google | 55.15% |
| 15 | [Qwen3.6 Plus](/models/qwen3-6-plus) | — | Alibaba | 54.63% |
| 16 | [Claude Sonnet 4.5 Thinking](/models/claude-sonnet-4-5-thinking) | — | Anthropic | 54.50% |
| 17 | [Qwen3.5 Plus Thinking](https://www.vals.ai/models/alibaba_qwen3.5-plus-thinking) | — | Alibaba | 54.48% |
| 18 | [Grok 4.3](/models/grok-4-3) | — | xAI | 53.81% |
| 19 | [Grok 4 0709](https://www.vals.ai/models/grok_grok-4-0709) | — | xAI | 53.51% |
| 20 | [GPT-5.4 mini](/models/gpt-5-4-mini) | xhigh reasoning | OpenAI | 53.41% |
| 21 | [GLM 5 Thinking](https://www.vals.ai/models/zai_glm-5-thinking) | — | Zhipu AI | 53.18% |
| 22 | [Qwen 3.6 Max (preview)](/models/qwen3-6-max-preview) | — | Alibaba | 52.78% |
| 23 | [Grok 4.1 Fast (Reasoning)](/models/grok-4-1-fast-reasoning) | — | xAI | 52.45% |
| 24 | [Grok 4.20 0309 Reasoning](https://www.vals.ai/models/grok_grok-4.20-0309-reasoning) | — | xAI | 52.30% |
| 25 | [GPT-5](https://www.vals.ai/models/openai_gpt-5-2025-08-07) | high reasoning | OpenAI | 52.15% |
| 26 | [GPT-5 mini](/models/gpt-5-mini) | high reasoning | OpenAI | 51.93% |
| 27 | [Gemma 4 31b It](https://www.vals.ai/models/google_gemma-4-31b-it) | high reasoning | Google | 50.79% |
| 28 | [Kimi K2.5 Thinking](https://www.vals.ai/models/kimi_kimi-k2.5-thinking) | — | Moonshot AI | 50.62% |
| 29 | [MiniMax M2.7](/models/minimax-m2-7) | — | MiniMax | 48.40% |
| 30 | [GPT-5.4 nano](/models/gpt-5-4-nano) | high reasoning | OpenAI | 47.80% |
| 31 | [Gemini 3 Flash Preview](https://www.vals.ai/models/google_gemini-3-flash-preview) | high reasoning | Google | 47.60% |
| 32 | [Claude Haiku 4.5 Thinking](/models/claude-haiku-4-5-thinking) | — | Anthropic | 46.93% |
| 33 | [Gemini 3.1 Flash Lite Preview](https://www.vals.ai/models/google_gemini-3.1-flash-lite-preview) | high reasoning | Google | 46.12% |
| 34 | [Mistral Medium 3.5](https://www.vals.ai/models/mistralai_mistral-medium-3.5) | high reasoning | Mistral AI | 46.11% |
| 35 | [Grok 4 Fast (Reasoning)](/models/grok-4-fast-reasoning) | — | xAI | 46.08% |
| 36 | [GLM-4.7](/models/glm-4-7) | — | Z.AI | 45.98% |
| 37 | [Qwen3.5 Flash](/models/qwen3-5-flash) | — | Alibaba | 45.64% |
| 38 | [Grok 4.1 Fast Non Reasoning](https://www.vals.ai/models/grok_grok-4-1-fast-non-reasoning) | — | xAI | 44.36% |
| 39 | [Qwen3 Max](/models/qwen3-max) | — | Alibaba | 44.30% |
| 40 | [Gemini 2.5 Pro](/models/gemini-2-5-pro) | — | Google | 41.59% |
| 41 | [MiniMax M2.5](/models/minimax-m2-5) | — | MiniMax | 38.58% |
| 42 | [Kimi K2 Thinking](https://www.vals.ai/models/kimi_kimi-k2-thinking) | — | Moonshot AI | 36.65% |
| 43 | [GLM-4.6](/models/glm-4-6) | — | Z.AI | 36.48% |
| 44 | [MiniMax M2.1](https://www.vals.ai/models/minimax_MiniMax-M2.1) | — | MiniMax | 33.35% |
| 45 | [GPT-OSS 120B](/models/gpt-oss-120b) | — | OpenAI | 21.54% |
| 46 | [Mistral Large 2512](https://www.vals.ai/models/mistralai_mistral-large-2512) | — | Mistral AI | 18.05% |
| 47 | [GPT-4o](/models/gpt-4o) | high reasoning | OpenAI | 8.06% |
| 48 | [Command A 03 2025](https://www.vals.ai/models/cohere_command-a-03-2025) | — | Cohere | 4.23% |
| 49 | [DeepSeek V3p2 Thinking](https://www.vals.ai/models/fireworks_deepseek-v3p2-thinking) | high reasoning | Fireworks AI | 2.35% |
| 50 | [Jamba Large 1.7](https://www.vals.ai/models/ai21labs_jamba-large-1.7) | — | AI21 Labs | 0.37% |
| 51 | [DeepSeek V3p2](https://www.vals.ai/models/fireworks_deepseek-v3p2) | none reasoning | Fireworks AI | 0.00% |

## FAQ

### What does Finance Agent v1.1 measure?

An archived Vals benchmark covering retrieval, numerical reasoning, financial modeling, market analysis, earnings, trends, and adjustments.

### Which model leads the published Finance Agent v1.1 snapshot?

Claude Opus 4.7 currently leads the published Finance Agent v1.1 snapshot with a score of 64.37%.

### How many models are evaluated on Finance Agent v1.1?

The June 4, 2026 contains 51 AI models.

### Does Finance Agent v1.1 affect BenchLM's overall score?

Not directly. Finance Agent v1.1 is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.