Claude Fable 5.1 vs Gemma 4 31B
As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in 5 of 5 shared categories: General LLM, Reasoning, Coding › Web dev, Long context, and Factuality.
Claude Fable 5.1
Yes. SOTA in Factuality (tied).
Gemma 4 31B
Yes. Yes on General LLM (≤32B); Reasoning (≤32B). Not the overall leader.
| Category | Claude Fable 5.1 | Gemma 4 31B |
|---|---|---|
| General LLM | #6 · Near-SOTA · General LLM Margin 3.191489361702125 LMArena leaderboard dataset · Oct 13, 2026 | #67 · #67 in General LLM Margin 35.63829787234043 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #5 · Near-SOTA · Reasoning Margin 3.191489361702125 LMArena leaderboard dataset · Oct 13, 2026 | #64 · #64 in Reasoning Margin 34.57446808510639 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #2 · Near-SOTA · Math Margin 2.2222222222222285 Epoch AI benchmarking hub · Sep 1, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| 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 | #90 · #90 in Coding › Web dev Margin 71.2 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #6 · Near-SOTA · Long context Margin 3.1914893617021107 LMArena leaderboard dataset · Oct 13, 2026 | #53 · #53 in Long context Margin 28.191489361702125 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 | #60 · #60 in Factuality Margin 35.46511627906976 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #3 · #3 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 1, 2026 | — |
Claude Fable 5.1: $20 per 1M blended tokens.
Gemma 4 31B: price per 1M tokens is unset in the catalog.
Claude Fable 5.1: closed weights.
Gemma 4 31B: open weights.
General LLM: As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in General LLM at #6 against #67.
Reasoning: As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in Reasoning at #5 against #64.
Coding › Web dev: As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in Coding › Web dev at #5 against #90.
Long context: As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in Long context at #6 against #53.
Factuality: As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in Factuality at #1 against #60.
Claude Fable 5.1 · Gemma 4 31B
Claude Fable 5.1 or Gemma 4 31B?
As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in 5 of 5 shared categories: General LLM, Reasoning, Coding › Web dev, Long context, and Factuality.
Claude Fable 5.1 or Gemma 4 31B for General LLM?
As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in General LLM at #6 against #67.
Claude Fable 5.1 or Gemma 4 31B for Reasoning?
As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in Reasoning at #5 against #64.
Claude Fable 5.1 or Gemma 4 31B for Coding › Web dev?
As of Oct 15, 2026, Claude Fable 5.1 leads Gemma 4 31B in Coding › Web dev at #5 against #90.