Verdict
Claude Opus 4.8 leads 15–1 across 16 shared benchmarks.
Claude Opus 4.8 15 · Claude Sonnet 4.6 1 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: Claude Opus 4.8 leads 3–1 across 4 shared reasoning benchmarks (largest gap: SimpleQA Verified, 39.5 vs 29 — single evaluator).
Agentic: Claude Opus 4.8 leads 2–0 across 2 shared agentic benchmarks (largest gap: APEX-Agents, 42.5 vs 23.7 — protocols undisclosed).
Coding: Claude Opus 4.8 leads 2–0 across 2 shared coding benchmarks (largest gap: DeepSWE, 58.97 vs 29.93 — single evaluator).
Unknown: Claude Opus 4.8 leads 2–0 across 2 shared unknown benchmarks (largest gap: ProofBench, 69 vs 45 — single evaluator).
Claude Opus 4.8 leads 15–1 across 16 shared benchmarks. Claude Opus 4.8 leads 15 benchmarks and Claude Sonnet 4.6 leads 1. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 4.8 and Claude Sonnet 4.6 have 16 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Opus 4.8 leads reasoning 3–1. Claude Opus 4.8 leads agentic 2–0.