Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 62 | |
| Mathematics | 88 | |
| Code | 70 | |
| Agents & real work | 86 | |
| Knowledge | 64 | |
| Long context | 95 | |
| Multimodal | 94 |
EditionUpdated daily
Ranking / GPT-5.6 Sol
GPT-5.6 Sol
OpenAI · Proprietary · context 1.05M. Ranked #8 of 26 with 779 ERAZ points out of 1000.
ERAZ rank#8/ 26
Points779/ 1000
Coverage100%
Benchmarks won0/ 14
Input price / M—
Output price / M—
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 49.5% | #10 / 26 | 81 | src ↗ |
| ARC-AGI-2 | 92.5% | #3 / 13 | 97 | src ↗ |
| ARC-AGI-3 | 7.8% | #6 / 9 | 12 | src ↗ |
| FrontierMath (Tiers 1-3) | 89% | #5 / 16 | 95 | src ↗ |
| FrontierMath (Tier 4) | 83% | #5 / 16 | 83 | src ↗ |
| SWE-bench Pro | 64.6% | #7 / 9 | 72 | src ↗ |
| FrontierSWE v2 | 32.2% | #8 / 14 | 49 | src ↗ |
| Terminal-Bench 2.1 | 85.8% | #2 / 12 | 98 | src ↗ |
| OSWorld 2.0 | 62.6% | #4 / 11 | 86 | src ↗ |
| GDPval-AA | 1735 | #9 / 23 | 85 | src ↗ |
| GPQA Diamond | 94.1% | #4 / 15 | 97 | src ↗ |
| AA-Omniscience | 22 | #12 / 26 | 47 | src ↗ |
| AA-LCR | 84% | #6 / 26 | 95 | src ↗ |
| MMMU-Pro | 83.4% | #6 / 14 | 94 | src ↗ |
Artificial Analysis Intelligence Index : — · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show GPT-5.6 Sol's ranking on your site or in a README. The badge updates every day.
