Claude Fable 5.1 vs GPT-5 Mini
As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in 6 of 6 shared categories: General LLM, Reasoning, Math, Long context, Factuality, and Abstraction (ARC).
| Category | Claude Fable 5.1 | GPT-5 Mini |
|---|---|---|
| General LLM | #6 · Near-SOTA · General LLM Margin 3.191489361702125 LMArena leaderboard dataset · Oct 13, 2026 | #165 · #165 in General LLM Margin 87.76595744680851 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #5 · Near-SOTA · Reasoning Margin 3.191489361702125 LMArena leaderboard dataset · Oct 13, 2026 | #169 · #169 in Reasoning Margin 90.42553191489361 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #2 · Near-SOTA · Math Margin 2.2222222222222285 Epoch AI benchmarking hub · Sep 1, 2026 | #21 · Was SOTA · Math Margin 44.44444444444444 Epoch AI benchmarking hub · Aug 7, 2025 |
| Science | — | #81 · #81 in Science Margin — Epoch AI benchmarking hub · Aug 7, 2025 |
| Coding | #3 · Near-SOTA · Coding Margin 18.181818181818187 Terminal-Bench Harbor Hub · Oct 6, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Coding › Agentic | #3 · Near-SOTA · Coding › Agentic Margin 18.181818181818187 Terminal-Bench Harbor Hub · Oct 6, 2026 | — |
| Coding › Web dev | #5 · Near-SOTA · Coding › Web dev Margin 3.200000000000003 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #6 · Near-SOTA · Long context Margin 3.1914893617021107 LMArena leaderboard dataset · Oct 13, 2026 | #187 · #187 in Long context Margin 99.46808510638297 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #6 · #6 in Vision Margin 18.421052631578945 Epoch AI benchmarking hub · Sep 1, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 |
| Factuality | #1 · Co-SOTA · Factuality Margin 0 LMArena leaderboard dataset · Oct 13, 2026 | #146 · #146 in Factuality Margin 85.46511627906978 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #3 · #3 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 1, 2026 | #41 · #41 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Aug 7, 2025 |
Claude Fable 5.1: $20 per 1M blended tokens.
GPT-5 Mini: $0.6875 per 1M blended tokens.
Claude Fable 5.1: closed weights.
GPT-5 Mini: closed weights.
General LLM: As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in General LLM at #6 against #165.
Reasoning: As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in Reasoning at #5 against #169.
Math: As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in Math at #2 against #21.
Long context: As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in Long context at #6 against #187.
Factuality: As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in Factuality at #1 against #146.
Abstraction (ARC): As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in Abstraction (ARC) at #3 against #41.
Claude Fable 5.1 or GPT-5 Mini?
As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in 6 of 6 shared categories: General LLM, Reasoning, Math, Long context, Factuality, and Abstraction (ARC).
Claude Fable 5.1 or GPT-5 Mini for General LLM?
As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in General LLM at #6 against #165.
Claude Fable 5.1 or GPT-5 Mini for Reasoning?
As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in Reasoning at #5 against #169.
Claude Fable 5.1 or GPT-5 Mini for Math?
As of Oct 15, 2026, Claude Fable 5.1 leads GPT-5 Mini in Math at #2 against #21.