Claude Opus 4.5 vs Claude Opus 4.8
As of Oct 15, 2026, Claude Opus 4.5 leads Claude Opus 4.8 in 0 of 7 shared categories.
Claude Opus 4.5
It used to be. Was SOTA in Reasoning.
Claude Opus 4.8
It used to be. Was SOTA in Coding › Web dev.
| Category | Claude Opus 4.5 | Claude Opus 4.8 |
|---|---|---|
| General LLM | #41 · #41 in General LLM Margin 21.808510638297875 LMArena leaderboard dataset · Oct 13, 2026 | #21 · #21 in General LLM Margin 11.170212765957444 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #30 · Was SOTA · Reasoning Margin 16.489361702127653 LMArena leaderboard dataset · Oct 13, 2026 | #10 · #10 in Reasoning Margin 5.851063829787236 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #16 · #16 in Math Margin 33.33333333333333 Epoch AI benchmarking hub · Nov 24, 2025 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Science | #68 · #68 in Science Margin — Epoch AI benchmarking hub · Nov 24, 2025 | #27 · #27 in Science Margin — Epoch AI benchmarking hub · May 28, 2026 |
| Coding | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #12 · #12 in Coding Margin 59.09090909090909 Terminal-Bench Harbor Hub · Oct 6, 2026 |
| Coding › Agentic | — | #12 · #12 in Coding › Agentic Margin 59.09090909090909 Terminal-Bench Harbor Hub · Oct 6, 2026 |
| Coding › Web dev | #58 · Was SOTA · Coding › Web dev Margin 45.6 LMArena leaderboard dataset · Oct 13, 2026 | #35 · Was SOTA · Coding › Web dev Margin 27.200000000000003 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #20 · Was SOTA · Long context Margin 10.63829787234043 LMArena leaderboard dataset · Oct 13, 2026 | #10 · Was SOTA · Long context Margin 5.319148936170208 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | — | #13 · #13 in Vision Margin 36.842105263157904 Epoch AI benchmarking hub · May 28, 2026 |
| Factuality | #40 · #40 in Factuality Margin 23.837209302325576 LMArena leaderboard dataset · Oct 13, 2026 | #24 · #24 in Factuality Margin 14.534883720930239 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #49 · #49 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Nov 24, 2025 | #12 · #12 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · May 28, 2026 |
Claude Opus 4.5: $10 per 1M blended tokens.
Claude Opus 4.8: $10 per 1M blended tokens.
Claude Opus 4.5: closed weights.
Claude Opus 4.8: closed weights.
General LLM: As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in General LLM at #21 against #41.
Reasoning: As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in Reasoning at #10 against #30.
Science: As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in Science at #27 against #68.
Coding › Web dev: As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in Coding › Web dev at #35 against #58.
Long context: As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in Long context at #10 against #20.
Factuality: As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in Factuality at #24 against #40.
Abstraction (ARC): As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in Abstraction (ARC) at #12 against #49.
Claude Opus 4.5 · Claude Opus 4.8
Claude Opus 4.5 or Claude Opus 4.8?
As of Oct 15, 2026, Claude Opus 4.5 leads Claude Opus 4.8 in 0 of 7 shared categories.
Claude Opus 4.5 or Claude Opus 4.8 for General LLM?
As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in General LLM at #21 against #41.
Claude Opus 4.5 or Claude Opus 4.8 for Reasoning?
As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in Reasoning at #10 against #30.
Claude Opus 4.5 or Claude Opus 4.8 for Science?
As of Oct 15, 2026, Claude Opus 4.8 leads Claude Opus 4.5 in Science at #27 against #68.