NeoHorse-1 4B beats its Qwen3.5 base on all ten tests, average score up 58.94 to 64.87
PrajwalTomar_ · x · 2026-09-16
In his TokenRhythm thread, Prajwal Tomar cites early numbers: across ten tests by TokenRhythm, NeoHorse-1 4B improved on its Qwen3.5 base in every single one, with the average moving from 58.94 to 64.87. He notes these are TokenRhythm's own results and he hasn't independently reproduced them.
He also describes testing OpenSquilla on an AI-built MVP before client handoff: it surfaced a production risk with the exact code, then self-corrected under challenge and passed a rerun.
More from Models
- 'You Can Feel the Gradient Slopes': Dev Contrasts Benchmaxxed RL Models vs General Ones — theteknosaur · 2026-11-02
- LightOnOCR-3 Launches: Tops FRBench, Adds Layout Structure and Chart Extraction — IgorCarron · 2026-11-02
- NVIDIA's Kumo Is a Family of Four Tabular Foundation Models, Not Just One — pandeyparul · 2026-11-02
- SemiAnalysis: safety classifiers are underrated — Meta's Muse tops cyber benchmark at 35.2% — ThomasScialom · 2026-11-02
- DeepSeek V4.1 Flash 1017 wins over a longtime closed-source-only user: fast, cheap, reliable — _bachrc · 2026-11-02
- Local quants vs Claude on 9 real private bugs: 3-bit costs thinking time, not score — FeydRowan · 2026-11-02