Grok 4.5 tops Ramp’s invoice test on 150,000 real business bills
elonmusk · x · 2026-07-25
Grok 4.5 is being pitched as strong for real-world work after a Ramp benchmark on 150,000 actual business invoices.
- Ramp scored models on whether they predicted every correction a human would make.
- Grok reportedly had the highest perfect-extraction rate, ahead of similarly priced Gemini Flash 3.6, GPT 5.6 Terra, and Sonnet 5.
- The task requires long-context reasoning over 100K+ tokens of invoice history, business memory, and human corrections.
- Ramp’s stated goal is zero-click accounts payable, where invoices are processed correctly without human intervention.
More from Models
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26