HLE-Diamond: Leaders Score 16-35 Points Higher on Reasoning, Max Effort Costs Up to 35x
ArtificialAnlys · x · 2026-10-30
Artificial Analysis added two dimensions to its HLE-Diamond leaderboard analysis:
- Reasoning vs knowledge: every model above 50% scores 16-35 points higher on reasoning than knowledge. GPT-6.1 Sol (max) shows the widest gap among leaders at 76% reasoning vs 41% knowledge.
- Effort vs cost: higher effort settings yield big gains at steep cost. Claude Opus 5.5 gains 26 points from low (42%) to max (68%) at 35x the cost per task; GPT-6 Astra gains 19 points from low (45%) to max (64%) at 11x the cost.
More from Models
- Grok Bot on Windows plagued by flashing messages, bot spam and voice issues — IndraVahan · 2026-10-30
- Altman: OpenAI Almost Ditched Token Pricing for an AWS-Style Bill, Users Refused — menhguin · 2026-10-30
- User math: $1 of Son costs 7x Opus on $20 plan, but tasks only 1.3x — alvelda · 2026-10-30
- Claude gets the right answer but can't prove time complexity — geoffreyirving · 2026-10-30
- Healthcare company's ops team burns 1.2B Opus tokens in a single day — RishabJainK · 2026-10-30
- Kimi K3.1 Pro leak teases open weights by Nov 4, 2026 as progress index reportedly tops Fable 5 — teortaxesTex · 2026-10-30