GPT-6.2 Sol coding score drops from 52 to 49, but costs 19% less per task
lxfater · x · 2026-11-18
Artificial Analysis benchmarked two generations of GPT Sol on Codex, both at max: the score fell from 52 to 49, roughly a 5.8% regression.
However, per-task API cost dropped from $1.51 to $1.22, about 19% cheaper.
A 19% price cut in exchange for a 5.8% capability drop — is that a trade worth taking?
More from Models
- Gemini 4 breakdown: Neon is 2x faster than Carbon but hallucinates more — teortaxesTex · 2026-11-19
- Gemini 4 Neon (High) beats Hydrogen and Carbon on AI SEO advice in hands-on test — gaganghotra_ · 2026-11-19
- Agents spent years hillclimbmaxxing while the human at the keyboard became an afterthought — tokenbender · 2026-11-19
- Speculation: Argon/Carbon/Neon may be nested distillations, with 'adapted' dodging 'post-trained' — teortaxesTex · 2026-11-19
- 6.2-Astra reportedly crushes contest benchmarks, finding a novel AWTF26 solution in 2 hours — i_dg23 · 2026-11-19
- KVARK Flash: a proxy that caps DeepSeek's thinking per request, 30-50% fewer tokens — Ill_Contribution_717 · 2026-11-19