Verdict
GPT-5.2 leads 12–6 across 18 shared benchmarks.
Gemini 3 Pro 6 · GPT-5.2 12 · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Reasoning: Gemini 3 Pro leads 4–1 across 5 shared reasoning benchmarks (largest gap: SimpleBench, 71.68 vs 34.96 — single evaluator).
Agentic: GPT-5.2 leads 2–0 across 2 shared agentic benchmarks (largest gap: APEX-Agents, 34.3 vs 18.4 — protocols undisclosed).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
Context Handling
“state-of-the-art reasoning, vision and spatial understanding, leading multilingual performance, and 1 million-token context window”
Multimodal
“It's the best model in the world for multimodal understanding and our most powerful agentic and vibe coding model yet”
Reasoning
“It's state-of-the-art in reasoning, built to grasp depth and nuance”
No vendor claims on file for GPT-5.2.
GPT-5.2 leads 12–6 across 18 shared benchmarks. Gemini 3 Pro leads 6 benchmarks and GPT-5.2 leads 12. Higher isn't always better — see the integrity caveats on each benchmark.
Gemini 3 Pro and GPT-5.2 have 18 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Gemini 3 Pro leads reasoning 4–1. GPT-5.2 leads agentic 2–0.