Compare / Inkling Small vs GLM 5.3
Inkling Small vs GLM 5.3
17 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Inkling Small | GLM 5.3 |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0075 | $0.0156 |
| BulletBenchmeasured by us | Games lost on time% of games | 0.0% | 83.3% |
| BulletBenchmeasured by us | Invalid moves% of moves | 7.2% | 0.0% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 529 | 33 |
| BulletBenchmeasured by us | Median move timemilliseconds | 0.6 s | 1.6 s |
| Arena (formerly LMArena)reported | Confirmed task successIPS effect estimate | -0.21 | 0.06 |
| Arena (formerly LMArena)reported | Praise over complaintIPS effect estimate | -0.21 | 0.06 |
| Arena (formerly LMArena)reported | SteerabilityIPS effect estimate | -0.12 | 0.03 |
| Arena (formerly LMArena)reported | Tool groundingIPS effect estimate | -0.00 | 0.00 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,425 | 1,468 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,408 | 1,474 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,313 | 1,456 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,445 | 1,516 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,393 | 1,480 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,405 | 1,480 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,344 | 1,470 |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 19.1% | 41.0% |
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.