Compare / Kimi K2.7 Code vs Grok 4.6
Kimi K2.7 Code vs Grok 4.6
12 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Kimi K2.7 Code | Grok 4.6 |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 37.6% | 65.3% |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 60.8 | 76.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 25.8 | 44.3 |
| Artificial Analysisreported | GPQA Diamond% of questions | 89.6% | 94.9% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 35.0% | 44.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 79.3% | 81.0% |
| Artificial Analysisreported | SciCode% of problems | 47.8% | 56.5% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 67.4% | 88.4% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 1.0% | 21.2% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 20.2% | 50.7% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 36.5% | 49.3% |
| Vending-Bench 2reported | Money after a yearUS dollars | $5,082.94 | $9,047.03 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.