Physical-Engineering's Last Exam (hidden test, structural)

Name: Physical-Engineering's Last Exam (hidden test, structural) results
Creator: Village

Professional Work · 2026-10-30

The 6 structural engineering tasks of Physical-Engineering's Last Exam's 56 hidden test tasks.

Benchmark source: Ple Bench

Top models (higher is better)

Model	Score	Source
Claude Opus 5.5	57.6	Physical-Engineering's Last Exam: Claude Opus 5.5 on openhands · Google
Claude Opus 5	52.3	Physical-Engineering's Last Exam: Claude Opus 5 on codex · Google
Claude Sonnet 5.5	52.2	Physical-Engineering's Last Exam: Claude Sonnet 5.5 on opencode · Google
Claude Fable 5	48.7	Physical-Engineering's Last Exam: Claude Fable 5 on openhands · Google
GPT-6 Astra	48.4	Physical-Engineering's Last Exam: GPT 6 Astra on codex · Google
Gemini 4 Argon	45.8	Physical-Engineering's Last Exam: Gemini 4 Argon on agy · Google
Gemini 3.8 Flash	33.9	Physical-Engineering's Last Exam: Gemini 3.8 Flash on openhands · Google
Grok 4.7	32.5	Physical-Engineering's Last Exam: Grok 4.7 on pi · Google
GLM-5.2	27.6	Physical-Engineering's Last Exam: GLM 5.2 on opencode · Google
Gemini 3.1 Pro Preview	12.9	Physical-Engineering's Last Exam: Gemini 3.1 Pro on claude-code · Google
Kimi K2 Thinking	4.5	Physical-Engineering's Last Exam: Kimi K2 Thinking on opencode · Google
Qwen3-Coder-480B-A35B-Instruct	3.1	Physical-Engineering's Last Exam: Qwen3 Coder 480B on openhands · Google
MiniMax M2	2.8	Physical-Engineering's Last Exam: MiniMax M2 on codex · Google
gpt-oss-120b	1.8	Physical-Engineering's Last Exam: gpt-oss 120B on hermes · Google
Qwen3 Next 80B A3B Instruct	1.1	Physical-Engineering's Last Exam: Qwen3-Next 80B on claude-code · Google
Gemma 4 26B A4B IT	0.7	Physical-Engineering's Last Exam: Gemma 4 26B on agy · Google
Llama 4 Maverick Instruct	0.0	Physical-Engineering's Last Exam: Llama 4 Maverick on agy · Google