Claude Haiku 5.5 Ranks Second on Intelligence Index but Burns Tokens
Artificial Analysis's evaluation shows Claude Haiku 5.5 (max) scoring an intelligence index of 43, ranking 2nd among 179 models, and reaching 1578 Elo on AA-Briefcase. However, it consumes about 162k output tokens per task, roughly triple that of GPT-6 Luna.
2026-10-08 ~ 2026-10-08 · 4 related posts
- Episode 1: Claude Haiku 5.5 Leaked in Claude Code, Priced Against GPT-6 Luna(2026-10-08, 3 posts)
- Episode 2: Anthropic Launches Claude Haiku 5.5 with 75% Lower Costs(2026-10-08, 34 posts)
- Episode 3: Claude Haiku 5.5 Ranks Second on Intelligence Index but Burns Tokens(2026-10-08, 4 posts)
- Claude Haiku 5.5 burns ~162k tokens per task, 3x GPT-6 Luna for similar scores — ArtificialAnlys · 2026-10-08
- Haiku 5.5 hits 1578 Elo on AA-Briefcase, within confidence range of GPT-6 Astra — ArtificialAnlys · 2026-10-08
- Haiku 5.5 reaches 1578 Elo on AA-Briefcase but uses far more tokens than rivals — ArtificialAnlys · 2026-10-08
- Claude Haiku 5.5 scores 43 on AA Intelligence Index, ranking #2 among 179 models — ArtificialAnlys · 2026-10-08