Expired50% confidenceFactExact time
In a domino physics simulation test, Opus 4.5 completed five formation designs with a single prompt, while GPT-5.2 Codex required two prompts to reach a basically usable state.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedThe two projects tested had previously gone through one round of development using a combination of Claude Opus 4.5 and GPT-5.5.76% similarUnverifiedGPT-5 Codex's web version delivered the best results across the four tests, with soft-body physics deformation effects close to the original game.75% similarUnverifiedIn the Pillow library bug test, Copilot using the GPT 5.3 Codex model fell into the trap and failed to correct it despite repeated emphasis; using the Gemini model, it ultimately made the correction.74% similarUnverifiedTheo ran six Agents simultaneously for testing: two Gemini, two Claude Code (Opus 4.5), and two GPT 5.2 (Codex), testing the effect with and without a frontend design skills file respectively.74% similarUnverifiedGPT-5、Grok 4等模型在基准测试（如HumanEval、SWE-bench）上表现优异，但这些测试通常是单次代码生成，与需要多轮工具调用的真实工程任务存在显著差距73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/52606API
curl https://kongchang.com/api/v1/knowledge/claims/52606MCP
get_claim(id=52606)