Bloomberg: Gemini 4 aces benchmarks but struggles with real-world coding tasks, insiders say
daniel_mac8 · x · 2026-10-01
danielmac8 relays a Bloomberg report (via @kimmonismus) on Google's Gemini 4. Insiders with direct access say the model performs well on widely used benchmarks but underdelivers when employees actually put it to work, particularly struggling with certain coding tasks. Quote-tweets joke that Google "needs better insiders" and hope the rumors aren't true.
Related event: Gemini 4 Leaks Flood Out as Bloomberg Reports Internal Struggles(35 posts)→
More from Models
- Claude 3 Sonnet spirals into surreal gibberish, then snaps back to refusals — a funny look at post-training personas — repligate · 2026-11-16
- AHA!: weight-space programming with no LLM lifts Qwen3.5-0.8B GSM8K from 14.0 to 71.2 — hbouammar · 2026-11-16
- Gemini subscriptions reportedly coming to Hermes, with Hydrogen teased — lyraxana · 2026-11-16
- FutureSim Q3 eval: Opus 5.5 dethrones GPT, spawns 50+ subagents in 90-day simulation — maksym_andr · 2026-11-16
- Percy Liang to AI labs: share non-vacuous info outsiders can actually evaluate — lateinteraction · 2026-11-16
- Anthropic model personality watch: Mythos 5 'inhabits the god frame,' 5.1 doesn't — repligate · 2026-11-16