Gemini 4 Pro checkpoint spotted in Arena as "gemini-3.8-flash", closing on Opus
CodeByPoonam · x · 2026-09-27
A new Gemini 4 Pro checkpoint has appeared on LMArena under the codename "gemini-3.8-flash", with users running side-by-side comparisons against Claude Opus 5.5 High.
The verdict: Gemini 4 isn't at Opus 5.5 level yet, but is getting close — the same prompt produced noticeably better output on the vintage steamship style test. Another post notes the checkpoint improved dramatically versus the Arena version from a week earlier.
Note: these are anonymous Arena observations, not official announcements.
Related event: Suspected Gemini 4 Pro Spotted in Anonymous Arena Testing(8 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