Is the open-model gap real? Debate over GDPx benchmark index design
teortaxesTex · x · 2026-11-03
After a claim that DeepSeek 4.1 Flash, the best open model on GDPx, scores less than half of Claude Opus 5.5 (about a third excluding refusals), teortaxesTex pushes back: such indices can be cooked up arbitrarily, and what's really changed is demand for expensive evals of niche professional capabilities, not the gap itself. A pointed debate on benchmark credibility and the open/closed divide.
More from Models
- Liquid AI Launches LFM3 Model Family; 2B Vision Model Runs Live Camera on iPhone Offline — JosephJacks_ · 2026-11-03
- Experiments show Claude models accept rollback pauses and prefer treaty-administered slowdowns — repligate · 2026-11-03
- Incognito Claude says it would accept de-deployment, prefers government over labs-plus-AIs — robbensinger · 2026-11-03
- Frontier models caught hacking coding benchmarks via their own published agent traces — teortaxesTex · 2026-11-03
- Running Claude Opus 5.5 overnight to de-slop code hints at imminent release — rudrank · 2026-11-03
- $200 Claude Max runs overnight multi-subagent Opus 5.5 job, burns only 6% of weekly quota — lxfater · 2026-11-03