Claude Sonnet 4.5 vs Claude Sonnet 5.5
As of Oct 15, 2026, Claude Sonnet 4.5 leads Claude Sonnet 5.5 in 0 of 7 shared categories.
Claude Sonnet 4.5
It used to be. Was SOTA in General LLM.
Claude Sonnet 5.5
Yes. SOTA in Coding (tied), Coding › Agentic (tied), and Vision (tied).
| Category | Claude Sonnet 4.5 | Claude Sonnet 5.5 |
|---|---|---|
| General LLM | #62 · Was SOTA · General LLM Margin 32.97872340425532 LMArena leaderboard dataset · Oct 13, 2026 | #29 · #29 in General LLM Margin 15.425531914893611 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #51 · Was SOTA · Reasoning Margin 27.65957446808511 LMArena leaderboard dataset · Oct 13, 2026 | #18 · #18 in Reasoning Margin 10.106382978723403 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #25 · #25 in Math Margin 53.333333333333336 Epoch AI benchmarking hub · Sep 29, 2025 | #4 · #4 in Math Margin 6.666666666666671 Epoch AI benchmarking hub · Sep 28, 2026 |
| Science | #82 · #82 in Science Margin — Epoch AI benchmarking hub · Sep 29, 2025 | #3 · #3 in Science Margin — Epoch AI benchmarking hub · Sep 28, 2026 |
| Coding | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 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 | #86 · Was SOTA · Coding › Web dev Margin 68 LMArena leaderboard dataset · Oct 13, 2026 | #3 · Near-SOTA · Coding › Web dev Margin 1.5999999999999943 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #34 · Was SOTA · Long context Margin 18.085106382978722 LMArena leaderboard dataset · Oct 13, 2026 | #11 · #11 in Long context Margin 5.851063829787236 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | — | #1 · Co-SOTA · Vision Margin 0 Epoch AI benchmarking hub · Sep 28, 2026 |
| Factuality | #61 · #61 in Factuality Margin 36.04651162790697 LMArena leaderboard dataset · Oct 13, 2026 | #17 · #17 in Factuality Margin 10.465116279069761 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #66 · #66 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 29, 2025 | — |
Claude Sonnet 4.5: $6 per 1M blended tokens.
Claude Sonnet 5.5: $4.000000000000001 per 1M blended tokens.
Claude Sonnet 4.5: closed weights.
Claude Sonnet 5.5: closed weights.
General LLM: As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in General LLM at #29 against #62.
Reasoning: As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in Reasoning at #18 against #51.
Math: As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in Math at #4 against #25.
Science: As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in Science at #3 against #82.
Coding › Web dev: As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in Coding › Web dev at #3 against #86.
Long context: As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in Long context at #11 against #34.
Factuality: As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in Factuality at #17 against #61.
Claude Sonnet 4.5 · Claude Sonnet 5.5
Claude Sonnet 4.5 or Claude Sonnet 5.5?
As of Oct 15, 2026, Claude Sonnet 4.5 leads Claude Sonnet 5.5 in 0 of 7 shared categories.
Claude Sonnet 4.5 or Claude Sonnet 5.5 for General LLM?
As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in General LLM at #29 against #62.
Claude Sonnet 4.5 or Claude Sonnet 5.5 for Reasoning?
As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in Reasoning at #18 against #51.
Claude Sonnet 4.5 or Claude Sonnet 5.5 for Math?
As of Oct 15, 2026, Claude Sonnet 5.5 leads Claude Sonnet 4.5 in Math at #4 against #25.