Finance Agent (Opus 4.6 System Card): leaderboard
Finance Agent results as reported in the Claude Opus 4.6 system card — Anthropic-run evaluation comparing a small set of frontier models.
Metric: Accuracy (%). Source: www-cdn.anthropic.com. Saturation forecast: Around November 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 (Thinking) | 60.7 | #63 (Claude Opus 4.6) |
| 2 | GPT-5.1 | 56.55 | #135 |
| 3 | Claude Sonnet 4.5 (Thinking) | 55.32 | #142 (Claude Sonnet 4.5) |
| 4 | Claude Opus 4.5 (Thinking) | 55.23 | #83 (Claude Opus 4.5) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=finance-agent-opus-4-6-system-card · How It Works · Data refreshed daily, snapshot 2026-10-20.