Grok 4.6 vs Grok 4.7
3 shared benchmark contexts with reported scores and primary source links.
Shared benchmarks
3| Benchmark | Grok 4.6 | Grok 4.7 |
|---|---|---|
40.4% | 46.3% | |
Evaluation details for CursorBench 4.0The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry. Grok 4.6 Grok 4.7 | ||
79.7% | 80.3% | |
Evaluation details for CyberGym OriginalThe recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry. Grok 4.6 Grok 4.7 | ||
DeepSWE 1.1Potentially non-equivalent: Evaluator sets differ. | 67.0%1.1 · DeepSWE Pass@1 DataCurve 65.9%1.1 · DeepSWE Pass@1 SpaceXAI | 71.0%1.1 · DeepSWE Pass@1 SpaceXAI |
Potentially non-equivalent · Evaluation details for DeepSWE 1.1Evaluator sets differ. Evaluation methodology is not recorded by the registry. Grok 4.6 Grok 4.7 | ||