Mystery Model Ox Alpha Review: Near-Fable Performance, Unique Vision/Logic Profile
Afinetheorem · x · 2026-08-22
Initial evaluation of the mystery model Ox Alpha:
- Positioning: Not quite at Fable or Sol level, but very close.
- Connections: Seems related to prior Zhipu GLM training (which is open source), but has a distinct post-training style.
- Performance: Uncorrelated with existing models on vision/logic benchmarks (though performs worse than Spark 1.2/Gemini/Fable).
- Focus: Shows signs of heavy post-training on computer tasks, though fails some straightforward science literature queries.
More from Models
- Nathan Lambert slams Meta's Muse Open License as 'trash' — natolambert · 2026-10-16
- Google launches Gemini 4 Argon to Ultra and Pro subscribers, touting physics and 3D skills — ShikharMurty · 2026-10-16
- Google gives X users early access to test Argon, not just companies — lyraxana · 2026-10-16
- Grok Voice 3.0 Tops Design Arena Speech Leaderboard, Up 7.4 Points — XFreeze · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- Meta open-sources Muse Spark: top US open model, scores just below DeepSeek — bindureddy · 2026-10-16