Verdict
Claude Opus 4.6 leads 14–4 across 18 shared benchmarks.
Claude Opus 4.6 14 · GLM-5.2 4 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: Claude Opus 4.6 leads 4–1 across 5 shared unknown benchmarks (largest gap: ProofBench, 50 vs 35 — single evaluator).
Reasoning: Claude Opus 4.6 leads 3–1 across 4 shared reasoning benchmarks (largest gap: ARC-AGI, 94 vs 77 — single evaluator).
Math: Evenly split 1–1 across 2 shared math benchmarks (largest gap: OTIS Mock AIME 2024-2025, 94.44 vs 86.38 — single evaluator).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
Coding
“The new Claude Opus 4.6 improves on its predecessor's coding skills”
Coding
“Advanced Coding with Flexible Effort: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency”
Context Handling
“We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9x at a 1M context length.”
General
“Pure Open: An MIT open-source license - no regional limits, technical access without borders”
Claude Opus 4.6 leads 14–4 across 18 shared benchmarks. Claude Opus 4.6 leads 14 benchmarks and GLM-5.2 leads 4. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 4.6 and GLM-5.2 have 18 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Claude Opus 4.6 leads unknown 4–1. Claude Opus 4.6 leads reasoning 3–1.