LLM Stats (Finance Agent v2): leaderboard
LLM Stats mirror of the Vals AI Finance Agent v2 benchmark, measuring financial-research agent accuracy on realistic analyst workflows over SEC filings and supporting documents.
Metric: Score (%). Source: llm-stats.com. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ling 3.0 Flash Fin | 59.81 | |
| 2 | Gemini 3.5 Flash | 57.86 | #60 |
| 3 | Muse Spark 1.1 | 57.2 | #52 |
| 4 | Claude Fable 5 | 56.31 | #16 |
| 5 | Mistral Large 4 | 54.7 | #94 |
| 6 | Claude Opus 4.8 | 53.92 | #37 |
| 7 | GPT-5.5 | 51.76 | #31 |
| 8 | Claude Opus 4.7 | 51.51 | #49 |
| 9 | Claude Sonnet 4.6 | 51.03 | #90 |
| 10 | Qwen3.7 Max | 48.35 |
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-finance-agent-v2 · How It Works · Data refreshed daily, snapshot 2026-10-20.