Verdict
GPT-6 Astra leads 9–0 across 9 shared benchmarks.
Gemini 3.8 Flash 0 · GPT-6 Astra 9 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Math: GPT-6 Astra leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 97.6 vs 21.95 — protocols undisclosed).
Reasoning: GPT-6 Astra leads 2–0 across 2 shared reasoning benchmarks (largest gap: SimpleQA Verified, 75.6 vs 69.7 — protocols undisclosed).
Unknown: GPT-6 Astra leads 2–0 across 2 shared unknown benchmarks (largest gap: ProofBench, 99 vs 48 — single evaluator).
GPT-6 Astra leads 9–0 across 9 shared benchmarks. Gemini 3.8 Flash leads 0 benchmarks and GPT-6 Astra leads 9. Higher isn't always better — see the integrity caveats on each benchmark.
Gemini 3.8 Flash and GPT-6 Astra have 9 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-6 Astra leads math 2–0. GPT-6 Astra leads reasoning 2–0.