AA-PersonalityBench: GLM-5.3 averages 7.4 em dashes per reply, Claude almost none
ArtificialAnlys · x · 2026-11-05
Artificial Analysis launched AA-PersonalityBench and shared an em-dash usage stat across benchmark responses.
- GLM-5.3 averages 7.4 em dashes per response, the highest of any model measured
- Claude Opus 5.5, Sonnet 5.5 and Haiku 5.5 use almost none—Opus 5.5 averages fewer than one every 40 responses
- Claude Fable 5.1 averages 6.4 per response
Full rankings and methodology are public on the AA-PersonalityBench page, where users can build their own personality rankings.
Related event: GLM-5.3 Tops Em Dash Usage Count While Claude Barely Uses Any(2 posts)→
More from Models
- Open-source TTS: Phonon models under 50M params run on-device with 7ms latency — alex_verem · 2026-11-05
- ElevenLabs sweeps all 5 new Voice Arena TTS leaderboards by 11-26 Elo points — alex_verem · 2026-11-05
- BioSimBench: frontier LLMs ace biology benchmarks but fail at predicting real cell experiments — alex_verem · 2026-11-05
- Grok and Claude Now Refuse to Root Your Own Devices, Citing Brick Risk — doooyle · 2026-11-05
- Nace AI offers 120% cashback to switch teams to Drex Max, claims 11x cost edge over Claude Code — testingcatalog · 2026-11-05
- Stanford benchmark: 18 AI models tested as teammates, best scores just 82.2/100 — james_y_zou · 2026-11-05