Google’s Gemini 4 Carbon is now available in the Cursor coding editor, where it scored 60.4% on CursorBench 4.0 at its highest reasoning setting, the best result on Cursor’s internal coding-agent leaderboard, according to AlphaSignal. Google says it also ranked first on Perplexity’s WANDR research benchmark at less than half the cost of the next-best model, though Cursor’s published table does not list Carbon’s per-task cost. Through November 30, Cursor is charging $2 per million input tokens and $10 per million output tokens; those rates double on December 1. Read more- https://alphasignal.ai/news/google-s-gemini-4-carbon-tops-cursor-s-coding-benchmark-at-half-the-price
Google’s Gemini 4 Carbon Tops Cursor’s Coding Benchmark at Half the Price
Google’s Gemini 4 Carbon is now available in the Cursor coding editor, where it scored 60.4% on CursorBench 4.0 at its highest reasoning setting, the best result on Cursor’s internal coding-agent leaderboard, according to AlphaSignal. Google says it also ranked first on Perplexity’s WANDR research benchmark at less than half…
+
+
+
+
+
+
Leave a Reply