Verdict
Grok 4.6 leads 7–6 across 13 shared benchmarks.
Grok 4.6 7 · Qwen 3.8 Max 6 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: Evenly split 2–2 across 4 shared unknown benchmarks (largest gap: DTBench, 95.55 vs 86.67 — single evaluator).
Coding: Grok 4.6 leads 2–0 across 2 shared coding benchmarks (largest gap: DeepSWE, 67.48 vs 57.46 — single evaluator).
Math: Qwen 3.8 Max leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 46.34 vs 31.71 — single evaluator).
Reasoning: Grok 4.6 leads 2–0 across 2 shared reasoning benchmarks (largest gap: SimpleQA Verified, 49.3 vs 45.8 — protocols undisclosed).
Grok 4.6 leads 7–6 across 13 shared benchmarks. Grok 4.6 leads 7 benchmarks and Qwen 3.8 Max leads 6. Higher isn't always better — see the integrity caveats on each benchmark.
Grok 4.6 and Qwen 3.8 Max have 13 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Grok 4.6 leads coding 2–0. Qwen 3.8 Max leads math 2–0.