Compare / Kimi K3 vs Grok 4.3
Kimi K3 vs Grok 4.3
19 results from 5 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Kimi K3 | Grok 4.3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,472 | 1,428 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,489 | 1,440 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,458 | 1,423 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,533 | 1,452 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,486 | 1,415 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,488 | 1,442 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,475 | 1,424 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 76.2 | 42.2 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 43.6 | 24.9 |
| Artificial Analysisreported | GPQA Diamond% of questions | 93.5% | 90.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 46.9% | 37.2% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 88.7% | 75.0% |
| Artificial Analysisreported | SciCode% of problems | 59.5% | 48.3% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 85.0% | 39.7% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 12.6% | 0.0% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 46.0% | 12.4% |
| GDP.pdfreported | Professional document tasks% of rubric | 19.0% | 8.0% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 50.6% | 33.2% |
| Vending-Bench 2reported | Money after a yearUS dollars | $5,165.03 | $35.26 |
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.