Verdict
Claude Fable 5.1 leads 16–2 across 18 shared benchmarks.
Claude Fable 5.1 16 · Gemini 3.8 Flash 2 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: Claude Fable 5.1 leads 5–0 across 5 shared unknown benchmarks (largest gap: Furniture Assembly, 57.14 vs 2.38 — protocols undisclosed).
Reasoning: Claude Fable 5.1 leads 2–1 across 3 shared reasoning benchmarks (largest gap: HLE, 43.8 vs 41.72 — protocols undisclosed).
Agentic: Claude Fable 5.1 leads 2–0 across 2 shared agentic benchmarks (largest gap: Remote Labor Index, 17.92 vs 5.83 — protocols undisclosed).
Coding: Claude Fable 5.1 leads 2–0 across 2 shared coding benchmarks (largest gap: FrontierSWE, 56.29 vs 19.63 — single evaluator).
Math: Claude Fable 5.1 leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 87.8 vs 21.95 — protocols undisclosed).
Claude Fable 5.1 leads 16–2 across 18 shared benchmarks. Claude Fable 5.1 leads 16 benchmarks and Gemini 3.8 Flash leads 2. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Fable 5.1 and Gemini 3.8 Flash have 18 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Fable 5.1 leads unknown 5–0. Claude Fable 5.1 leads agentic 2–0.