Claude Haiku 4.5 vs Claude Sonnet 5.5
As of Oct 14, 2026, Claude Haiku 4.5 leads Claude Sonnet 5.5 in 0 of 6 shared categories.
Claude Haiku 4.5
#78 Best recorded rank: #78 in Abstraction (ARC), as of Oct 14, 2026.
Claude Sonnet 5.5
Yes. SOTA in co-SOTA in Coding, co-SOTA in Coding › Agentic and co-SOTA in Vision.
| Category | Claude Haiku 4.5 | Claude Sonnet 5.5 |
|---|---|---|
| General LLM | #104 · #104 in General LLM Margin 70.74829931972789 LMArena leaderboard dataset · Oct 13, 2026 | #27 · #27 in General LLM Margin 18.367346938775512 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #91 · #91 in Reasoning Margin 63.013698630136986 LMArena leaderboard dataset · Oct 13, 2026 | #18 · #18 in Reasoning Margin 13.013698630136986 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #4 · #4 in Math Margin 6.666666666666671 Epoch AI benchmarking hub · Sep 28, 2026 |
| Science | #109 · #109 in Science Margin — Epoch AI benchmarking hub · Oct 15, 2025 | #3 · #3 in Science Margin — Epoch AI benchmarking hub · Sep 28, 2026 |
| Coding | #— · Not enough data Margin — Scale Labs leaderboards · Oct 14, 2026 | #1 · Co-SOTA · Coding Margin 0 Terminal-Bench Harbor Hub · Oct 6, 2026 |
| Coding › Agentic | — | #1 · Co-SOTA · Coding › Agentic Margin 0 Terminal-Bench Harbor Hub · Oct 6, 2026 |
| Coding › Web dev | #92 · #92 in Coding › Web dev Margin 85.04672897196262 LMArena leaderboard dataset · Oct 13, 2026 | #3 · Near-SOTA · Coding › Web dev Margin 1.8691588785046775 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #84 · #84 in Long context Margin 57.142857142857146 LMArena leaderboard dataset · Oct 13, 2026 | #11 · #11 in Long context Margin 7.482993197278915 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | — | #1 · Co-SOTA · Vision Margin 0 Epoch AI benchmarking hub · Sep 28, 2026 |
| Factuality | #97 · #97 in Factuality Margin 73.13432835820896 LMArena leaderboard dataset · Oct 13, 2026 | #16 · #16 in Factuality Margin 12.68656716417911 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #78 · #78 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Oct 15, 2025 | — |
Claude Haiku 4.5: $2.0000000000000004 per 1M blended tokens.
Claude Sonnet 5.5: $4.000000000000001 per 1M blended tokens.
Claude Haiku 4.5: closed weights.
Claude Sonnet 5.5: closed weights.
General LLM: As of Oct 14, 2026, Claude Sonnet 5.5 leads Claude Haiku 4.5 in General LLM at #27 against #104.
Reasoning: As of Oct 14, 2026, Claude Sonnet 5.5 leads Claude Haiku 4.5 in Reasoning at #18 against #91.
Science: As of Oct 14, 2026, Claude Sonnet 5.5 leads Claude Haiku 4.5 in Science at #3 against #109.
Coding › Web dev: As of Oct 14, 2026, Claude Sonnet 5.5 leads Claude Haiku 4.5 in Coding › Web dev at #3 against #92.
Long context: As of Oct 14, 2026, Claude Sonnet 5.5 leads Claude Haiku 4.5 in Long context at #11 against #84.
Factuality: As of Oct 14, 2026, Claude Sonnet 5.5 leads Claude Haiku 4.5 in Factuality at #16 against #97.
Claude Haiku 4.5 · Claude Sonnet 5.5
Claude Haiku 4.5 or Claude Sonnet 5.5?
As of Oct 14, 2026, Claude Haiku 4.5 leads Claude Sonnet 5.5 in 0 of 6 shared categories.
Claude Haiku 4.5 or Claude Sonnet 5.5 for General LLM?
As of Oct 14, 2026, Claude Sonnet 5.5 leads Claude Haiku 4.5 in General LLM at #27 against #104.
Claude Haiku 4.5 or Claude Sonnet 5.5 for Reasoning?
As of Oct 14, 2026, Claude Sonnet 5.5 leads Claude Haiku 4.5 in Reasoning at #18 against #91.
Claude Haiku 4.5 or Claude Sonnet 5.5 for Science?
As of Oct 14, 2026, Claude Sonnet 5.5 leads Claude Haiku 4.5 in Science at #3 against #109.