Compare / Kimi K3 vs Grok 4.20
Kimi K3 vs Grok 4.20
7 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 K3 | Grok 4.20 |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 43.6 | 25.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 93.5% | 91.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 46.9% | 34.5% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 88.7% | 69.0% |
| tau2-benchreported | Consistency (pass^4)% of tasks | 17.5% | 8.2% |
| tau2-benchreported | Task success (pass^1)% of tasks | 37.1% | 18.0% |
| Vending-Bench 2reported | Money after a yearUS dollars | $5,165.03 | $4,662.85 |
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.