# Model ML completes finance work more efficiently with GPT-5.6 Sol

Model ML's Composite eval also found GPT-5.6 Sol used 36% fewer tokens per Excel workbook than Opus 5.

- GPT-5.6 Sol completed the PowerPoint workflow in 100% of test cases vs 76% for Opus 5, and cleared the professional-readiness gate in 43.3% of cases vs 26.7%.
- Model ML expanded GPT-5.6 Sol in production, including workflows previously handled by Opus 4.8.
- At one global asset manager, a bespoke tearsheet that took an analyst about an hour now takes about five minutes.
- Model ML agents processed virtual data rooms containing more than 100,000 rows and hundreds of files in one pass.

## Why it matters

Finance teams using Model ML can now produce editable, traceable decks and workbooks with fewer tokens, moving straight into review instead of rebuilding deliverables.

## Sources

- [OpenAI: Model ML completes finance work more efficiently with GPT-5.6 Sol](https://openai.com/index/model-ml)

---

Summarized by dstilled on 2026-08-10. https://dstilled.ai/story/94bbaf8c-88a7-44fc-bf59-28f3052f8585