Compare / Kimi K2 0905 vs Grok 4.3
Kimi K2 0905 vs Grok 4.3
17 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 0905 | Grok 4.3 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,403 | 1,428 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,404 | 1,440 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,382 | 1,423 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,417 | 1,452 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,390 | 1,415 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,419 | 1,442 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,382 | 1,424 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 15.3 | 24.9 |
| Artificial Analysisreported | GPQA Diamond% of questions | 76.7% | 90.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 6.4% | 37.2% |
| Artificial Analysisreported | IFBench% of instructions | 41.7% | 83.3% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 53.0% | 75.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 23.5% | 37.9% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 73.4% | 97.7% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 22.0% | 21.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.31 | 0.34 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 54.4 | 57.7 |
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.