Sonnet 5.5 called a bad release as GPT-6.1 sol scores higher at 33% lower cost
haider1 · x · 2026-09-30
Citing Artificial Analysis Intelligence Index data, haider1 argues Sonnet 5.5 is a bad release: at medium effort it scored 41 using 19k output tokens vs GPT-6.1 sol's 48 at 8k; at high effort 47/34k vs 50/13k. Cost per task: $0.72 for 6.1 sol max vs $1.08 for Sonnet 5.5 high — 33% cheaper while scoring higher.
More from Models
- Stealth Model 'silicon-2' Surfaces in Devin, Suspected to Be Anthropic's Next Model — kimmonismus · 2026-11-16
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- Nathan Lambert calls out Ethan Mollick for 'selectively ignoring' Kimi in model comparisons — natolambert · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- Unsloth Q8 crushes default Q3 in a self-hosted test over 331 financial PDFs — No_Cartographer3953 · 2026-11-16