Verdict
GPT-6 Astra leads 9–1 across 15 shared benchmarks.
GPT-6.1 Sol 1 · GPT-6 Astra 9 · 5 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Unknown: GPT-6 Astra leads 3–0 across 5 shared unknown benchmarks (largest gap: EBR-bench, 76.19 vs 54.29 — protocols undisclosed).
Reasoning: GPT-6 Astra leads 2–0 across 3 shared reasoning benchmarks (largest gap: SimpleQA Verified, 75.6 vs 73.9 — protocols undisclosed).
Math: GPT-6.1 Sol leads 1–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 100 vs 97.6 — protocols undisclosed).
GPT-6 Astra leads 9–1 across 15 shared benchmarks. GPT-6.1 Sol leads 1 benchmark and GPT-6 Astra leads 9, with 5 tied. Higher isn't always better — see the integrity caveats on each benchmark.
GPT-6.1 Sol and GPT-6 Astra have 15 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-6 Astra leads unknown 3–0. GPT-6 Astra leads reasoning 2–0.