GPT-6.1 Sol benchmarks: 5 tiers score 42-52, cost-per-task varies 5.5x
ArtificialAnlys · x · 2026-09-30
Artificial Analysis benchmarked OpenAI's GPT-6.1 Sol release: five tiers (max/xhigh/high/medium/low) score 42–52 on the Intelligence Index v4.3.2. The low tier is fastest (71 t/s, 1.96s TTFT) and cheapest at $0.13 per task, while max costs $0.72 — a 5.5x spread. All tiers support text+image input, 1M context, and reasoning.
More from Models
- Users report Grok Bot is now nearly as fast as Muse — yunta_tsai · 2026-09-30
- banteg: model recovers 88 decompiled functions per hour that recompile to exact original machine code — banteg · 2026-09-30
- Will AI subscriptions hit $1,000/month next year? Priced against a $200k salary, some say it's cheap — RachelVT42 · 2026-09-30
- Early user on Grok's Dot Bot: 'You can immediately feel the difference' — jdjohnson · 2026-09-30
- Qwen Is Quietly Becoming the Language Backbone of 100+ Audio Models — Acceptable-Cycle4645 · 2026-09-30
- Enterprise evals: GPT-6.1 beats Opus 5.5 with 2x speed and 40% lower price — npew · 2026-09-30