Artificial Analysis launches Decision Index: Claude Opus 5.5 tops at 79
LeviTurk · x · 2026-10-15
Artificial Analysis introduced its Decision Index, a weighted average of AA-Omniscience-Decision, HLE-MultiChoice, When2Call, and WildGuardTest, measuring how well models make decisions across 26 entries.
Per the leaderboard chart, dedicated decision models sweep the top eight spots: Claude Opus 5.5 (Max Ops Default) leads with 79, followed by Claude Opus 5.5 (Low Ops Default) at 76, GPTo1 Sol[6.1] and GPTo1 Sol[6] at 71 each, and several Claude Haiku 5.5 variants between 61 and 68.
Among language models, Jev 1.13 scores 58, Gemini 4 TB (Reasoning) 56, and GPT-6 (Low) 54, with specialized decision models clearly outperforming general-purpose LLMs.
Related event: Artificial Analysis Launches Decision Index for Decision Models(3 posts)→
More from Models
- Gemini 4 Argon falls short as drop-in replacement for Opus 5.5 and Grok 4.7, user reports — triviatroy · 2026-10-15
- Why games are a real, taste-aware coding benchmark, not just a gimmick — vitaliychiley · 2026-10-15
- First Hands-On Impressions of Unannounced 'Gemini 4 Argon' Point to Strong Frontend Skills — zacharynado · 2026-10-15
- Claude pushes usage-credit pop-up while weekly limit banner shows only ~35% used — RyanMorrisonJer · 2026-10-15
- Designer finds Opus 5.5 picks up nuanced aesthetic taste with startling speed — floguo · 2026-10-15
- GLM-5.3 unprompted reasons about how its actions affect its future training, worries Apollo — MariusHobbhahn · 2026-10-15