Grok 4.6 Tops CursorBench with 6X Lower Cost Than Rivals
XFreeze · x · 2026-08-22
Grok 4.6 achieved the #1 spot on CursorBench 3.2 with a score of 70.8% and remarkable efficiency. Priced at $2.81 per task, it costs roughly 6X less than Fable 5 Max ($17.32) and nearly 3X less than Opus 5 Max ($8.23). This combination of top-tier intelligence and low compute cost makes it highly powerful for long-horizon agentic coding tasks.
More from Models
- Claude Security Now Powered by Mythos 5 for Cross-File Vulnerability Scanning — claudeai · 2026-08-22
- Hands-on with Ox Alpha: Impressive Performance in Pi Harness — omarsar0 · 2026-08-22
- Model Self-Talk Artifacts Linked to Synthetic Data Training — ctjlewis · 2026-08-22
- Ornith 1.5 35B live on RunInfra: 262K context, ~$0.02/1M effective input with cache — alejandroll10 · 2026-08-22
- Developer doubts Ox-alpha performance, suspects marketing stunt — bindureddy · 2026-08-22
- SemiAnalysis Deep Dive: Are Open Models Catching Up to Closed Frontier? — JosephJacks_ · 2026-08-22