Claude Opus 5 vs GPT-6 Astra
- Score
- Claude Opus 5 5 · GPT-6 Astra 17 · 1 tied — higher isn't always better; check the caveats.
- Shared
- 23 benchmarks measured for both models
- Integrity
- 21 of 23 graded A or B
Reported scores — protocols may differ. How we compare
Each bar is drawn on its benchmark's own scale — the ceiling the record states where it has one (of 100), otherwise the best score recorded on that benchmark (rel. 2103). The margin is in points: + is Claude Opus 5, - is GPT-6 Astra.
Game Playing: GPT-6 Astra leads 4–0 across 4 shared game playing benchmarks (largest gap: Chess Puzzles, 74.75 vs 40.03 — protocols undisclosed).
Coding: Claude Opus 5 leads 2–1 across 3 shared coding benchmarks (largest gap: MirrorCode, 87.78 vs 60 — protocols undisclosed).
Reasoning: GPT-6 Astra leads 3–0 across 3 shared reasoning benchmarks (largest gap: SimpleQA Verified, 75.6 vs 59.9 — protocols undisclosed).
Unknown: Claude Opus 5 leads 2–0 across 3 shared unknown benchmarks (largest gap: DTBench, 96.45 vs 95.55 — single evaluator).
Abstract Reasoning: GPT-6 Astra leads 2–0 across 2 shared abstract reasoning benchmarks (largest gap: ARC-AGI-2, 95 vs 90.42 — protocols undisclosed).
Machine Learning: GPT-6 Astra leads 2–0 across 2 shared machine learning benchmarks (largest gap: WeirdML v3, 60.05 vs 36.15 — single evaluator).
Math: GPT-6 Astra leads 2–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 97.6 vs 73.17 — protocols undisclosed).
GPT-6 Astra leads 17–5 across 23 shared benchmarks. Claude Opus 5 leads 5 benchmarks and GPT-6 Astra leads 17, with 1 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 5 and GPT-6 Astra have 23 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
GPT-6 Astra leads game playing 4–0. GPT-6 Astra leads reasoning 3–0.