Claude Opus 4.7 vs GPT-4.5 Preview
As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in 6 of 6 shared categories: General LLM, Reasoning, Math, Science, Long context, and Abstraction (ARC).
Claude Opus 4.7
Close. Near-SOTA in Reasoning, rank #4.
GPT-4.5 Preview
It used to be. Was SOTA in General LLM.
| Category | Claude Opus 4.7 | GPT-4.5 Preview |
|---|---|---|
| General LLM | #5 · Near-SOTA · General LLM Margin 3.401360544217681 LMArena leaderboard dataset · Oct 13, 2026 | #62 · Was SOTA · General LLM Margin 42.17687074829932 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #4 · Near-SOTA · Reasoning Margin 3.4246575342465775 LMArena leaderboard dataset · Oct 13, 2026 | #93 · Was SOTA · Reasoning Margin 64.38356164383562 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #10 · #10 in Math Margin 20 Epoch AI benchmarking hub · Apr 16, 2026 | #38 · #38 in Math Margin 84.44444444444444 Epoch AI benchmarking hub · Feb 27, 2025 |
| Science | #34 · #34 in Science Margin — Epoch AI benchmarking hub · Apr 16, 2026 | #92 · #92 in Science Margin — Epoch AI benchmarking hub · Feb 27, 2025 |
| Coding | #— · Not enough data Margin — Epoch AI benchmarking hub · Apr 16, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Coding › Web dev | #32 · Was SOTA · Coding › Web dev Margin 28.971962616822424 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #4 · Near-SOTA · Long context Margin 2.7210884353741562 LMArena leaderboard dataset · Oct 13, 2026 | #76 · Was SOTA · Long context Margin 51.70068027210884 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #20 · Was SOTA · Vision Margin 55.26315789473684 Epoch AI benchmarking hub · Apr 16, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 |
| Factuality | #12 · #12 in Factuality Margin 9.701492537313428 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Abstraction (ARC) | #11 · #11 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Apr 16, 2026 | #83 · #83 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Feb 27, 2025 |
Claude Opus 4.7: $10 per 1M blended tokens.
GPT-4.5 Preview: price per 1M tokens is unset in the catalog.
Claude Opus 4.7: closed weights.
GPT-4.5 Preview: closed weights.
General LLM: As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in General LLM at #5 against #62.
Reasoning: As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in Reasoning at #4 against #93.
Math: As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in Math at #10 against #38.
Science: As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in Science at #34 against #92.
Long context: As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in Long context at #4 against #76.
Abstraction (ARC): As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in Abstraction (ARC) at #11 against #83.
Claude Opus 4.7 · GPT-4.5 Preview
Claude Opus 4.7 or GPT-4.5 Preview?
As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in 6 of 6 shared categories: General LLM, Reasoning, Math, Science, Long context, and Abstraction (ARC).
Claude Opus 4.7 or GPT-4.5 Preview for General LLM?
As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in General LLM at #5 against #62.
Claude Opus 4.7 or GPT-4.5 Preview for Reasoning?
As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in Reasoning at #4 against #93.
Claude Opus 4.7 or GPT-4.5 Preview for Math?
As of Oct 14, 2026, Claude Opus 4.7 leads GPT-4.5 Preview in Math at #10 against #38.