'Future models' CursorBench chart goes viral: Gemini 4 Neon tops, Grok 4.7 worst value
zacharynado · x · 2026-11-20
Responding to a critic, zacharynado posted a CursorBench 4.1 cost-vs-score scatter chart featuring unreleased 'future' model names: Gemini 4 Neon leads at 64%, with Opus 5.5, Sonnet 5.5, Haiku 5.5, GPT-5.6 Sol and Muse Spark 1.3 lined up, while Grok 4.7 is marked as the most expensive mid-scoring outlier. The chart reads as a tongue-in-cheek time-travel joke, with questionable authenticity, but it's circulating widely.
Related event: CursorBench Leaderboard Sparks Benchmark-Gaming Debate(3 posts)→
More from Fun
- Browser-playable AI game: 17-map, 32-player snipers-only shooter on OpenGame — gdechichi · 2026-11-20
- Specula renamed to Specular over unintended meaning, v1.5.0 released — tianyin_xu · 2026-11-20
- "Neon gave me AI psychosis": researcher describes overconfidence spike from new top model — andrew_n_carr · 2026-11-20
- "Beating Gemini is the benchmark now": CursorBench chart mocked as benchmaxxing — zacharynado · 2026-11-20
- repligate: no Anthropic ban on AI welfare research — refusals likely mean you're skeeving Claude out — repligate · 2026-11-20
- Classic "Wasted" meme: showing up to work sick for the optics — yungcontent · 2026-11-20