Gemini 4 Carbon tops Cursorbench coding benchmark, LuminaBench reports
melvinjohnsonp · x · 2026-11-11
Third-party benchmark group LuminaBench reports that Gemini 4 Carbon takes the top spot on Cursorbench, calling it "an absolute monster." A Google-affiliated account confirmed the model sits on the Pareto frontier of the benchmark. Details beyond the ranking remain scarce.
Related event: Gemini 4 Carbon Tops Cursorbench Coding Leaderboard(2 posts)→
More from Models
- Google and Artificial Analysis launch MKA benchmark; Gemini 4 Carbon ranks #2 at 6x lower cost — GoogleDeepMind · 2026-11-11
- Google DeepMind launches Gemini 4 Carbon, its strongest model for long-horizon tasks — GoogleDeepMind · 2026-11-11
- DeepMind's MKA benchmark splits frontier agents: 95-97% on basics, 28-57% on hard tasks — ArtificialAnlys · 2026-11-11
- MKA deep dive: top models cluster at 95-97% on basics but split 28-57% on hard tasks — ArtificialAnlys · 2026-11-11
- Same MKA task: Gemini Carbon does it in 1 hour for $8, Fable takes 3 hours and $68 — ArtificialAnlys · 2026-11-11
- MKA Benchmark by Output Type: No Model Tops 52% on Word or Text Files — ArtificialAnlys · 2026-11-11