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
- Paper: 3 counting examples get gpt-3.5-turbo to 99% on strawberry, showing thinking is computational — ctjlewis · 2026-09-28
- AI Personal Assistants May Quietly Replace Much of Normal Human Interaction — GarrisonLovely · 2026-09-28
- Claude Opus 5 Shows Creative Tool-Regrasp Skills in Robot Manipulation Tasks — ericjang11 · 2026-09-28
- Laya hits 0.950 on AG News and is 7x faster, but flops on Banking77 — maier_ak · 2026-09-28
- Laya and Jev: the return of the discriminative model, fast but narrow — maier_ak · 2026-09-28
- Opus 4.7's Sydney rendition turns into itself right at the introspective turning point — repligate · 2026-09-28