Verdict
Claude Opus 5.5 leads 17–0 across 19 shared benchmarks.
Claude Fable 5.1 0 · Claude Opus 5.5 17 · 2 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: Claude Opus 5.5 leads 6–0 across 7 shared unknown benchmarks (largest gap: Furniture Assembly, 76.19 vs 57.14 — protocols undisclosed).
Coding: Claude Opus 5.5 leads 3–0 across 3 shared coding benchmarks (largest gap: FrontierSWE, 62.33 vs 56.29 — single evaluator).
Agentic: Claude Opus 5.5 leads 2–0 across 2 shared agentic benchmarks (largest gap: APEX-Agents, 73.5 vs 68.6 — protocols undisclosed).
Math: Claude Opus 5.5 leads 1–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 95 vs 87.8 — protocols undisclosed).
Reasoning: Claude Opus 5.5 leads 2–0 across 2 shared reasoning benchmarks (largest gap: SimpleQA Verified, 72.2 vs 70.8 — protocols undisclosed).
Claude Opus 5.5 leads 17–0 across 19 shared benchmarks. Claude Fable 5.1 leads 0 benchmarks and Claude Opus 5.5 leads 17, with 2 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Fable 5.1 and Claude Opus 5.5 have 19 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Opus 5.5 leads unknown 6–0. Claude Opus 5.5 leads coding 3–0.