Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 71 | |
| Mathematics | — | |
| Code | 61 | |
| Agents & real work | 62 | |
| Knowledge | 60 | |
| Long context | 100 | |
| Multimodal | 91 |
EditionUpdated daily
Ranking / Kimi K3
Kimi K3
Moonshot AI · Open · context 1.05M. Ranked #13 of 26 with 642 ERAZ points out of 1000.
ERAZ rank#13/ 26
Points642/ 1000
Coverage65%
Benchmarks won1/ 14
Input price / M$3
Output price / M$15
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 46.9% | #14 / 26 | 76 | src ↗ |
| ARC-AGI-2 | 60.4% | #13 / 13 | 64 | src ↗ |
| ARC-AGI-3 | not published | — | — | |
| FrontierMath (Tiers 1-3) | not published | — | — | |
| FrontierMath (Tier 4) | not published | — | — | |
| SWE-bench Pro | not published | — | — | |
| FrontierSWE v2 | 25.9% | #11 / 14 | 40 | src ↗ |
| Terminal-Bench 2.1 | 80.9% | #6 / 12 | 93 | src ↗ |
| OSWorld 2.0 | not published | — | — | |
| GDPval-AA | 1533 | #21 / 23 | 62 | src ↗ |
| GPQA Diamond | 93.5% | #6 / 15 | 96 | src ↗ |
| AA-Omniscience | 19.7 | #13 / 26 | 42 | src ↗ |
| AA-LCR | 88.7% | #1 / 26 | 100 | src ↗ |
| MMMU-Pro | 80.5% | #9 / 14 | 91 | src ↗ |
Artificial Analysis Intelligence Index : 43.6 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show Kimi K3's ranking on your site or in a README. The badge updates every day.
