Compare / Kimi K3 vs GPT-5.2
Kimi K3 vs GPT-5.2
16 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 | GPT-5.2 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,472 | 1,442 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,489 | 1,444 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,458 | 1,391 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,533 | 1,475 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,486 | 1,427 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,488 | 1,437 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,475 | 1,411 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 43.6 | 30.4 |
| Artificial Analysisreported | GPQA Diamond% of questions | 93.5% | 90.3% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 46.9% | 37.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 88.7% | 82.7% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 46.0% | 11.1% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 50.6% | 37.1% |
| tau2-benchreported | Consistency (pass^4)% of tasks | 17.5% | 18.6% |
| tau2-benchreported | Task success (pass^1)% of tasks | 37.1% | 32.2% |
| Vending-Bench 2reported | Money after a yearUS dollars | $5,165.03 | $3,591.33 |
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.