Anthropic
Claude Haiku 5.5 benchmark results
5 results on 4 benchmarks from 2 sources.
Also listed as: claude-haiku-5.5-high · claude-haiku-5-5_max · Claude Haiku 5.5 (max) · claude-haiku-5-5_xhigh · Claude Haiku 5.5 (xhigh) · claude-haiku-5-5_high · Claude Haiku 5.5 (high) · claude-haiku-5-5_unknown · Claude Haiku 5.5 (unknown)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena WebDev | 1587 | 30 | Overall; 978 votes; 95% CI 1567–1607“claude-haiku-5.5-high” | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 89.7% | 47 | Epoch AI run, accuracy; effort: max | Independent run | Oct 9, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 98.9% | 20 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh | Independent run | Oct 7, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 97.2% | 36 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: high | Independent run | Oct 7, 2026 |
| Humanity's Last Exam | 30.1% | 13 | Compiled by Epoch AI; effort: unknown | Third-party compilation via Epoch AI | Oct 7, 2026 |
FAQ
Where do these Claude Haiku 5.5 scores come from?
From Epoch AI Benchmarking Hub and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.