Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 69 | |
| Mathematics | 47 | |
| Code | 60 | |
| Agents & real work | 89 | |
| Knowledge | 52 | |
| Long context | 90 | |
| Multimodal | — |
EditionUpdated daily
Ranking / GLM-5.3
GLM-5.3
Z.ai · Open · context 1M. Ranked #15 of 26 with 613 ERAZ points out of 1000.
ERAZ rank#15/ 26
Points613/ 1000
Coverage69%
Benchmarks won0/ 14
Input price / M$1.40
Output price / M$4.40
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 42.3% | #21 / 26 | 69 | src ↗ |
| ARC-AGI-2 | not published | — | — | |
| ARC-AGI-3 | not published | — | — | |
| FrontierMath (Tiers 1-3) | 68.8% | #12 / 16 | 73 | src ↗ |
| FrontierMath (Tier 4) | 29.3% | #12 / 16 | 29 | src ↗ |
| SWE-bench Pro | not published | — | — | |
| FrontierSWE v2 | 30.2% | #9 / 14 | 46 | src ↗ |
| Terminal-Bench 2.1 | 71.5% | #10 / 12 | 82 | src ↗ |
| OSWorld 2.0 | not published | — | — | |
| GDPval-AA | 1769 | #7 / 23 | 89 | src ↗ |
| GPQA Diamond | 91.7% | #13 / 15 | 93 | src ↗ |
| AA-Omniscience | 14.3 | #16 / 26 | 31 | src ↗ |
| AA-LCR | 79.7% | #22 / 26 | 90 | src ↗ |
| MMMU-Pro | not published | — | — |
Artificial Analysis Intelligence Index : 44.8 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show GLM-5.3's ranking on your site or in a README. The badge updates every day.
