Compare / Kimi K2.7 Code vs GPT-5.4
Kimi K2.7 Code vs GPT-5.4
13 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 | GPT-5.4 |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 37.6% | 52.4% |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 60.8 | 71.1 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 25.8 | 39.0 |
| Artificial Analysisreported | GPQA Diamond% of questions | 89.6% | 92.0% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 35.0% | 43.7% |
| Artificial Analysisreported | IFBench% of instructions | 63.1% | 73.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 79.3% | 82.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 67.4% | 78.3% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 44.7% | 57.6% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 20.2% | 39.6% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 90.1% | 87.1% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 36.5% | 45.1% |
| Vending-Bench 2reported | Money after a yearUS dollars | $5,082.94 | $6,144.18 |
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.