Independent evaluator of AI models on professional tasks. Maintains Finance Agent, the Vals Index and Vibe Code Bench. On LLM Stats it maintains 7 benchmarks, led by Finance Agent v2, Finance Agent and Vals Finance Agent v2. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which Vals AI benchmarks count toward the LLM Stats Score?

Finance Agent v2, Finance Agent, Vals Finance Agent v2, Harvey's Legal Agent Benchmark, Finance Agent v1.1, Vals Index and 1 more count toward the LLM Stats Score. Only benchmarks admitted to the core set move the main leaderboard; the rest are shown for transparency.

Which models lead Vals AI's benchmarks?

Ling 3.0 Flash Fin leads Finance Agent v2 at 59.8% (28 models scored), Claude Opus 4.7 leads Finance Agent at 64.4% (8 models scored) and Gemini 4 Argon leads Vals Finance Agent v2 at 65.4% (6 models scored). Each benchmark page lists the full ranking and how the results were produced.

Where are Vals AI's official benchmark results?

Vals AI's official site is https://www.vals.ai. Each benchmark page on LLM Stats links to that benchmark's own paper or leaderboard, and shows the scores next to every other benchmark so models can be compared on one page.

Vals AI Benchmarks: Finance Agent v2

Maintained by Vals AI

7 benchmarks

Finance Agent
Finance Agent is a benchmark for evaluating AI models on agentic financial analysis tasks, testing their ability to process financial data, perform calculations, and generate accurate analyses across various financial domains.
reasoning finance agents Counts toward the LLM Stats Score
Leader
Claude Opus 4.764.4%
Models scored
8
Finance Agent v1.1
Finance Agent v1.1 is an agentic financial-analysis benchmark that evaluates models on real-world finance workflows, including retrieving and reasoning over financial documents and performing multi-step calculations.
reasoning finance agents Counts toward the LLM Stats Score
Leader
Ling 3.0 Flash Fin69.2%
Models scored
3
Finance Agent v2
Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.
reasoning finance agents Counts toward the LLM Stats Score
Leader
Ling 3.0 Flash Fin59.8%
Models scored
28
Vals Finance Agent v2
Vals Finance Agent v2 evaluates AI agents on realistic financial analyst tasks.
knowledge reasoning finance agents Counts toward the LLM Stats Score
Leader
Gemini 4 Argon65.4%
Models scored
6
Vals Index
Vals Index measures economic impact across finance, coding, legal, and tax work, with every sector weighted by its contribution to U.S. GDP.
knowledge reasoning agents Counts toward the LLM Stats Score
Leader
Gemini 4 Carbon70.4%
Models scored
2
Vibe Code Bench
Vibe Code Bench is a Vals AI agentic coding benchmark evaluating models on end-to-end coding workflows.
agents code Counts toward the LLM Stats Score
Leader
Gemini 4 Argon91.9%
Models scored
1
Harvey's Legal Agent Benchmark
Primary maintainer Harvey
Harvey's Legal Agent Benchmark evaluates AI agents on complex legal workflows and reports the all-pass rate.
knowledge legal reasoning agents Counts toward the LLM Stats Score
Leader
Kimi K3.1 Pro23.7%
Models scored
5

In one line

Vals AI maintains Finance Agent (counts toward the LLM Stats Score, 8 models scored), Finance Agent v1.1 (counts toward the LLM Stats Score, 3 models scored), Finance Agent v2 (counts toward the LLM Stats Score, 28 models scored), Vals Finance Agent v2 (counts toward the LLM Stats Score, 6 models scored), Vals Index (counts toward the LLM Stats Score, 2 models scored), Vibe Code Bench (counts toward the LLM Stats Score, 1 model scored) and Harvey's Legal Agent Benchmark (counts toward the LLM Stats Score, 5 models scored). It ships no models of its own on LLM Stats.

Vals AI: AI benchmarks & research