Claude Opus 4.8 vs GPT-4.5 Preview
As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in 5 of 5 shared categories: General LLM, Reasoning, Science, Long context, and Abstraction (ARC).
Claude Opus 4.8
It used to be. Was SOTA in Coding › Web dev.
GPT-4.5 Preview
It used to be. Was SOTA in General LLM.
| Category | Claude Opus 4.8 | GPT-4.5 Preview |
|---|---|---|
| General LLM | #21 · #21 in General LLM Margin 11.170212765957444 LMArena leaderboard dataset · Oct 13, 2026 | #79 · Was SOTA · General LLM Margin 42.02127659574468 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #10 · #10 in Reasoning Margin 5.851063829787236 LMArena leaderboard dataset · Oct 13, 2026 | #121 · Was SOTA · Reasoning Margin 64.8936170212766 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #38 · #38 in Math Margin 84.44444444444444 Epoch AI benchmarking hub · Feb 27, 2025 |
| Science | #27 · #27 in Science Margin — Epoch AI benchmarking hub · May 28, 2026 | #92 · #92 in Science Margin — Epoch AI benchmarking hub · Feb 27, 2025 |
| Coding | #12 · #12 in Coding Margin 59.09090909090909 Terminal-Bench Harbor Hub · Oct 6, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Coding › Agentic | #12 · #12 in Coding › Agentic Margin 59.09090909090909 Terminal-Bench Harbor Hub · Oct 6, 2026 | — |
| Coding › Web dev | #35 · Was SOTA · Coding › Web dev Margin 27.200000000000003 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #10 · Was SOTA · Long context Margin 5.319148936170208 LMArena leaderboard dataset · Oct 13, 2026 | #93 · Was SOTA · Long context Margin 49.468085106382986 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #13 · #13 in Vision Margin 36.842105263157904 Epoch AI benchmarking hub · May 28, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 |
| Factuality | #24 · #24 in Factuality Margin 14.534883720930239 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Abstraction (ARC) | #12 · #12 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · May 28, 2026 | #83 · #83 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Feb 27, 2025 |
Claude Opus 4.8: $10 per 1M blended tokens.
GPT-4.5 Preview: price per 1M tokens is unset in the catalog.
Claude Opus 4.8: closed weights.
GPT-4.5 Preview: closed weights.
General LLM: As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in General LLM at #21 against #79.
Reasoning: As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in Reasoning at #10 against #121.
Science: As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in Science at #27 against #92.
Long context: As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in Long context at #10 against #93.
Abstraction (ARC): As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in Abstraction (ARC) at #12 against #83.
Claude Opus 4.8 · GPT-4.5 Preview
Claude Opus 4.8 or GPT-4.5 Preview?
As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in 5 of 5 shared categories: General LLM, Reasoning, Science, Long context, and Abstraction (ARC).
Claude Opus 4.8 or GPT-4.5 Preview for General LLM?
As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in General LLM at #21 against #79.
Claude Opus 4.8 or GPT-4.5 Preview for Reasoning?
As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in Reasoning at #10 against #121.
Claude Opus 4.8 or GPT-4.5 Preview for Science?
As of Oct 15, 2026, Claude Opus 4.8 leads GPT-4.5 Preview in Science at #27 against #92.