Compare / GPT-5.4 Nano vs Inkling Small
GPT-5.4 Nano vs Inkling Small
18 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | GPT-5.4 Nano | Inkling Small |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0050 | $0.0075 |
| BulletBenchmeasured by us | Games lost on time% of games | 66.7% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 3.1% | 7.2% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 33 | 529 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.1 s | 0.6 s |
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0025 | $0.0077 |
| BulletBenchmeasured by us | Games lost on time% of games | 75.0% | 0.0% |
| BulletBenchmeasured by us | Invalid moves% of moves | 4.0% | 5.3% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 197 | 571 |
| BulletBenchmeasured by us | Median move timemilliseconds | 1.0 s | 0.6 s |
| Arena (formerly LMArena)reported | OverallArena rating | 1,418 | 1,425 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,405 | 1,408 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,335 | 1,313 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,438 | 1,445 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,387 | 1,393 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,401 | 1,405 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,362 | 1,344 |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 11.7% | 19.1% |
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.