Compare / Kimi K2.7 Code vs gpt-oss-120b
Kimi K2.7 Code vs gpt-oss-120b
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 K2.7 Code | gpt-oss-120b |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 37.6% | 4.4% |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 60.8 | 30.4 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 25.8 | 11.6 |
| Artificial Analysisreported | GPQA Diamond% of questions | 89.6% | 78.2% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 35.0% | 19.6% |
| Artificial Analysisreported | IFBench% of instructions | 63.1% | 69.0% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 79.3% | 52.0% |
| Artificial Analysisreported | SciCode% of problems | 47.8% | 34.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 67.4% | 26.2% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 1.0% | 0.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 44.7% | 23.5% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 20.2% | 12.8% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 90.1% | 65.8% |
| Vending-Bench 2reported | Money after a yearUS dollars | $5,082.94 | $-21.53 |
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.