Category scores
Out of 100: 100 = the best tracked model in the category.
| Reasoning | 52 | |
| Mathematics | 77 | |
| Code | 80 | |
| Agents & real work | 68 | |
| Knowledge | 32 | |
| Long context | 94 | |
| Multimodal | 91 |
EditionUpdated daily
Ranking / GPT-5.6 Terra
GPT-5.6 Terra
OpenAI · Proprietary · context 1.05M. Ranked #10 of 26 with 671 ERAZ points out of 1000.
ERAZ rank#10/ 26
Points671/ 1000
Coverage93%
Benchmarks won0/ 14
Input price / M$2
Output price / M$12
Points over time
| Day | Points | Change |
|---|
Results on each benchmark
| Benchmark | Score | Rank | Out of 100 | Source |
|---|---|---|---|---|
| Humanity's Last Exam | 42.9% | #19 / 26 | 70 | src ↗ |
| ARC-AGI-2 | 83.9% | #9 / 13 | 88 | src ↗ |
| ARC-AGI-3 | 0.8% | #8 / 9 | 1 | src ↗ |
| FrontierMath (Tiers 1-3) | 84.9% | #9 / 16 | 91 | src ↗ |
| FrontierMath (Tier 4) | 68.3% | #9 / 16 | 68 | src ↗ |
| SWE-bench Pro | 63.4% | #8 / 9 | 71 | src ↗ |
| FrontierSWE v2 | not published | — | — | |
| Terminal-Bench 2.1 | 77.5% | #7 / 12 | 89 | src ↗ |
| OSWorld 2.0 | 50.2% | #7 / 11 | 69 | src ↗ |
| GDPval-AA | 1583 | #17 / 23 | 68 | src ↗ |
| GPQA Diamond | 92.5% | #11 / 15 | 94 | src ↗ |
| AA-Omniscience | 0.1 | #23 / 26 | 0 | src ↗ |
| AA-LCR | 83% | #10 / 26 | 94 | src ↗ |
| MMMU-Pro | 80.7% | #8 / 14 | 91 | src ↗ |
Artificial Analysis Intelligence Index : 42.1 · Source page ↗
Nearby models in the ranking
</> Embed this ranking
Show GPT-5.6 Terra's ranking on your site or in a README. The badge updates every day.
