Retrieved PHREEQC output lowers GPT agent accuracy on fixed simulations
GPT-5.1 and GPT-5.2 lose 11.3 and 7.9 points via a section index, while two Claude models show no detectable drop.
55
Product
PHREEQC
- Mentions · 7d1
- Mentions · 30d2
- All mentions2
- First seenOct 18, 2026
- Last mentioned6d ago
Timeline
2 articles · newest firstRetrieved PHREEQC reports cost some GPT agents accuracy
GPT-5.1 and GPT-5.2 lost 11.3 and 7.9 points reading reports via a section index; Claude models did not.
52
Appears with
- USGSorganization · 2
- GPT-5.1ai model · 2
- Claude Opus 4.6ai model · 2
- Claude Sonnet 4.6ai model · 2
- GPT-5.4ai model · 2
- GPT-5.2ai model · 2
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.