Gemini 4 aces benchmarks but struggles on real-world coding tasks, say insiders
kimmonismus · x · 2026-10-01
Per Bloomberg, Gemini 4 scores well on widely used benchmarks but underperforms when Google employees actually use it, with sources citing weakness on certain coding tasks. Insiders are split on whether it has caught up to OpenAI and Anthropic — a fresh case of the benchmark-vs-reality gap.
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