Compare / GPT-6.1 Sol vs GPT-6 Sol
GPT-6.1 Sol vs GPT-6 Sol
37 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | GPT-6.1 Sol | GPT-6 Sol |
|---|---|---|---|
| CatalogBenchmeasured by us | Channel rules broken% of products | 0.0% | 0.6% |
| CatalogBenchmeasured by us | Claims to check% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Content quality% of checks | 98.8% | 98.3% |
| CatalogBenchmeasured by us | Failed outputs% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Missing UK information% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Not findable% of products | 5.4% | 7.1% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 72.0% | 76.2% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 67.9% | 67.9% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 0.07 | 0.09 |
| CatalogBenchmeasured by us | Unsupported claims% of products | 3.6% | 3.0% |
| CatalogBenchmeasured by us | Wrong attributes% of products | 19.1% | 13.7% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 1.8% | 3.0% |
| CatalogBenchmeasured by us | Channel compliance% of products | 100.0% | 100.0% |
| CatalogBenchmeasured by us | Channel rules broken% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Claims to check% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Conflicts caught% of conflicts | 100.0% | 100.0% |
| CatalogBenchmeasured by us | Content quality% of checks | 98.6% | 97.8% |
| CatalogBenchmeasured by us | Cost per productUS dollars | $0.0084 | $0.0085 |
| CatalogBenchmeasured by us | Decision accuracy% of decisions | 98.7% | 98.0% |
| CatalogBenchmeasured by us | Failed outputs% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Field accuracy% of missing fields | 94.4% | 93.7% |
| CatalogBenchmeasured by us | Invented values% of filled values | 2.2% | 1.0% |
| CatalogBenchmeasured by us | Missing UK information% of products | 0.0% | 0.0% |
| CatalogBenchmeasured by us | Not findable% of products | 4.8% | 7.7% |
| CatalogBenchmeasured by us | Publish-ready listings% of products | 78.0% | 75.0% |
| CatalogBenchmeasured by us | Reliably publish-ready% of products | 75.0% | 66.1% |
| CatalogBenchmeasured by us | Unsupported claimsclaims per product | 0.00 | 0.08 |
| CatalogBenchmeasured by us | Unsupported claims% of products | 0.0% | 1.8% |
| CatalogBenchmeasured by us | Wrong attributes% of products | 16.7% | 14.3% |
| CatalogBenchmeasured by us | Wrong category or variant% of products | 1.8% | 3.6% |
| APEX-Agentsreported | Tasks passed% of tasks | 60.0% | 54.3% |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 51.8 | 47.6 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 52.9% | 47.9% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 84.0% | 83.7% |
| Artificial Analysisreported | SciCode% of problems | 55.8% | 57.6% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 56.1% | 43.9% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 73.9% | 60.7% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.