Haiku 5.5 hits 1578 Elo on AA-Briefcase, within confidence range of GPT-6 Astra
ArtificialAnlys · x · 2026-10-08
Artificial Analysis published a full breakdown of Claude Haiku 5.5's results across individual Intelligence Index evaluations and effort settings. Notably, Haiku 5.5 (max) reaches 1578 Elo on AA-Briefcase, their private frontier knowledge-work benchmark, within the confidence intervals of GPT-6 Astra (max) and Claude Fable 5.1 (high) — showing the small model nearing flagship territory on realistic knowledge work.
Related event: Claude Haiku 5.5 scores near GPT-6 on knowledge work, at a token cost(3 posts)→
More from Models
- OpenRouter launches decision model rankings, typesafeai leads all categories — multiply_matrix · 2026-10-08
- Vik Paruchuri calls out model copying: inspiration doesn't let you rename it and change the license — VikParuchuri · 2026-10-08
- Haiku 5.5 costs 20x less than Sonnet 5.5, dev uses it for parallel sub-agents — RLanceMartin · 2026-10-08
- 100 classic texts tested: Pangram flags Victor Hugo poem as 100% AI after one line removed — GolinoHudson · 2026-10-08
- Haiku 5.5 at max reasoning burns more tokens than Opus 5.5 max, user finds — haider1 · 2026-10-08
- Requesting Anthropic's CVP auto-suspends your account, appeal restores it — dyn___ · 2026-10-08