# 9to5Google — Google stands by Gemini 4 performance as some claim it ‘struggles’ in real-world use

- Company: 9to5Google (9to5google.com)
- Announced: 2026-10-01T14:10:00+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://9to5google.com/2026/10/01/gemini-4-struggle-report/
- Record: https://forck.live/items/16964-google-stands-by-gemini-4-performance-as-some-claim-it-struggles-in-real-world
- Subject: Reporting
- Models affected: Gemini 4, Gemini 4 Argon
- Pricing: $4 per 1M input tokens and $20 per 1M output tokens

Google responded to a Bloomberg report that some employees found Gemini 4's real-world performance inconsistent with its benchmark scores, particularly in coding tasks. Google stated it would be inaccurate to say Gemini 4 is underperforming in coding, and a DeepMind executive reaffirmed the model is at the frontier. The report notes a split among employees, with some confident in the model's frontier status and others concerned it lags behind competitors.

## Evidence

Verbatim from https://9to5google.com/2026/10/01/gemini-4-struggle-report/:

> The report cites Googlers who found that the model "does less well when employees actually put it to work," and that it "struggles to handle certain coding tasks."

---

Record: https://forck.live/items/16964-google-stands-by-gemini-4-performance-as-some-claim-it-struggles-in-real-world
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md