Grok 4.6
9th on DeepSWE v1.1 Best (medium) at 67.5%, about $3.45 mean per task.
xAI · Proprietary · Fetched 2026-10-10
Benchmark scores
Boards older than 90 days are not counted as recommendationsBenchmarkSettingScoreRankCostAs of
Use it or not
Why
- DeepSWE top ten, cheaper than the Anthropic front on that board.
When not
- A different row from Grok 4.7; use 4.7 for WebDev.