AIFeatured4 min read
Model race
The LiveBench top four are separated by 2.2 points. The cost difference is brutal.
GPT-5.6 Sol takes the overall crown on LiveBench with an 82.4 average, but Claude Fable 5 trails by just 1.6 points at nearly three times the cost. The real story is how the pack below has thinned out, and where the dollar smarts stop.
2026-07-22