Verdict
Claude Fable 5.1 leads 14–2 across 19 shared benchmarks.
Claude Fable 5.1 14 · GPT-5.6 Sol 2 · 3 tied · 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 6 shared unknown benchmarks (largest gap: Furniture Assembly, 57.14 vs 38.1 — protocols undisclosed).
Coding: Claude Fable 5.1 leads 3–0 across 3 shared coding benchmarks (largest gap: MirrorCode, 73.3 vs 20 — single evaluator).
Math: Claude Fable 5.1 leads 1–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 87.8 vs 82.93 — protocols undisclosed).
Reasoning: Claude Fable 5.1 leads 1–0 across 2 shared reasoning benchmarks (largest gap: SimpleQA Verified, 70.8 vs 69.7 — protocols undisclosed).
Claude Fable 5.1 leads 14–2 across 19 shared benchmarks. Claude Fable 5.1 leads 14 benchmarks and GPT-5.6 Sol leads 2, with 3 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Fable 5.1 and GPT-5.6 Sol have 19 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 coding 3–0.