Same model over timeSingle-run anecdoteAI Coding
Eiffel Tower benchmark, launch vs Oct 3 vs Oct 22 — Claude Opus 5.5 (at launch) vs Claude Opus 5.5 (Oct 3) vs Claude Opus 5.5 (Oct 22)
Scoreboard3
- Claude Opus 5.5Anthropic
- Written as “Opus 5.5”
- Launch run
- Claude Opus 5.5Anthropic
- Written as “Opus 5.5”
- Oct 3 run
- Claude Opus 5.5Anthropic
- Written as “Opus 5.5”
- “Today” in the post, dated by the post (UTC)
Eiffel Tower benchmark, launch vs Oct 3 vs Oct 22The post doesn’t quote the prompt wording.
They say each run looks worse than the one before, and that the model now burns tokens faster.
@EnvolDev’s view (paraphrased)
Claude Opus 5.5 runs the author’s Eiffel Tower benchmark with the same prompt at launch, on Oct 3 and again on Oct 22, shown together in one video.
Same model, same prompt, run on different dates: one sample each, not a controlled test. Model outputs vary from run to run, so the poster’s claim is not verified here. All same-model-over-time posts.
The post, itemised
- Kind
- Side-by-side
- Task
- Eiffel Tower benchmark, launch vs Oct 3 vs Oct 22
- Category
- 3D & Shaders
- Mode
- Not stated
- Posted
- Video length
- 20 s
- Likes
- 1,602
- Views
- 354,880
- Bookmarks
- 352
- Sponsored
- No
NotesThe launch and Oct 3 runs were first posted on 2026-10-03.
Related
Posted by @EnvolDev on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
