Compare / Kimi K2.6 vs Kimi K2.7 Code
Kimi K2.6 vs Kimi K2.7 Code
14 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Kimi K2.6 | Kimi K2.7 Code |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 61.8 | 60.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 27.0 | 25.8 |
| Artificial Analysisreported | GPQA Diamond% of questions | 91.1% | 89.6% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 37.5% | 35.0% |
| Artificial Analysisreported | IFBench% of instructions | 76.0% | 63.1% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 81.0% | 79.3% |
| Artificial Analysisreported | SciCode% of problems | 51.5% | 47.8% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 65.9% | 67.4% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.5% | 1.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 43.9% | 44.7% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 23.3% | 20.2% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 95.9% | 90.1% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 34.9% | 36.5% |
| Vending-Bench 2reported | Money after a yearUS dollars | $6,204.57 | $5,082.94 |
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.