Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 76 | |
| Mathematics | — | |
| Code | — | |
| Agents & real work | 66 | |
| Knowledge | 55 | |
| Long context | 100 | |
| Multimodal | 85 |
EditionUpdated daily
Ranking / Step 5 Preview
Step 5 Preview
StepFun · Open · context 1M. Ranked #14 of 26 with 639 ERAZ points out of 1000.
ERAZ rank#14/ 26
Points639/ 1000
Coverage48%
Benchmarks won0/ 14
Input price / M$1
Output price / M$2.70
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 46.5% | #15 / 26 | 76 | src ↗ |
| ARC-AGI-2 | not published | — | — | |
| ARC-AGI-3 | not published | — | — | |
| FrontierMath (Tiers 1-3) | not published | — | — | |
| FrontierMath (Tier 4) | not published | — | — | |
| SWE-bench Pro | not published | — | — | |
| FrontierSWE v2 | not published | — | — | |
| Terminal-Bench 2.1 | not published | — | — | |
| OSWorld 2.0 | not published | — | — | |
| GDPval-AA | 1566 | #19 / 23 | 66 | src ↗ |
| GPQA Diamond | 93.5% | #7 / 15 | 96 | src ↗ |
| AA-Omniscience | 16.4 | #14 / 26 | 35 | src ↗ |
| AA-LCR | 88.3% | #2 / 26 | 100 | src ↗ |
| MMMU-Pro | 76.4% | #13 / 14 | 85 | src ↗ |
Artificial Analysis Intelligence Index : 43.7 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show Step 5 Preview's ranking on your site or in a README. The badge updates every day.
