Claude Opus 5.5 vs Claude Sonnet 4
As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in 5 of 5 shared categories: General LLM, Reasoning, Science, Long context, and Abstraction (ARC).
Claude Opus 5.5
Yes. SOTA in co-SOTA in Reasoning, co-SOTA in Coding, co-SOTA in Coding › Agentic, Coding › Web dev, co-SOTA in Long context and co-SOTA in Factuality.
Claude Sonnet 4
#35 Best current rank: #35 in Math, as of Oct 14, 2026.
| Category | Claude Opus 5.5 | Claude Sonnet 4 |
|---|---|---|
| General LLM | #2 · Near-SOTA · General LLM Margin 1.3605442176870781 LMArena leaderboard dataset · Oct 13, 2026 | #126 · #126 in General LLM Margin 85.71428571428571 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #1 · Co-SOTA · Reasoning Margin 0 LMArena leaderboard dataset · Oct 13, 2026 | #115 · #115 in Reasoning Margin 79.45205479452055 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #35 · #35 in Math Margin 77.77777777777777 Epoch AI benchmarking hub · May 22, 2025 |
| Science | #31 · #31 in Science Margin — Epoch AI benchmarking hub · Sep 22, 2026 | #97 · #97 in Science Margin — Epoch AI benchmarking hub · May 22, 2025 |
| Coding | #1 · Co-SOTA · Coding Margin 0 Terminal-Bench Harbor Hub · Oct 6, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Coding › Agentic | #1 · Co-SOTA · Coding › Agentic Margin 0 Terminal-Bench Harbor Hub · Oct 6, 2026 | — |
| Coding › Web dev | #1 · SOTA · Coding › Web dev Margin 0 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #1 · Co-SOTA · Long context Margin 0 LMArena leaderboard dataset · Oct 13, 2026 | #94 · #94 in Long context Margin 63.945578231292515 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #4 · Near-SOTA · Vision Margin 13.15789473684211 Epoch AI benchmarking hub · Sep 22, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 |
| Factuality | #1 · Co-SOTA · Factuality Margin 0 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Abstraction (ARC) | #1 · #1 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 22, 2026 | #67 · #67 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · May 22, 2025 |
Claude Opus 5.5: $8.000000000000002 per 1M blended tokens.
Claude Sonnet 4: $6 per 1M blended tokens.
Claude Opus 5.5: closed weights.
Claude Sonnet 4: closed weights.
General LLM: As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in General LLM at #2 against #126.
Reasoning: As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in Reasoning at #1 against #115.
Science: As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in Science at #31 against #97.
Long context: As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in Long context at #1 against #94.
Abstraction (ARC): As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in Abstraction (ARC) at #1 against #67.
Claude Opus 5.5 · Claude Sonnet 4
Claude Opus 5.5 or Claude Sonnet 4?
As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in 5 of 5 shared categories: General LLM, Reasoning, Science, Long context, and Abstraction (ARC).
Claude Opus 5.5 or Claude Sonnet 4 for General LLM?
As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in General LLM at #2 against #126.
Claude Opus 5.5 or Claude Sonnet 4 for Reasoning?
As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in Reasoning at #1 against #115.
Claude Opus 5.5 or Claude Sonnet 4 for Science?
As of Oct 14, 2026, Claude Opus 5.5 leads Claude Sonnet 4 in Science at #31 against #97.