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

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

Professional Work · 2026-10-30

The 9 civil engineering tasks of Physical-Engineering's Last Exam's 56 hidden test tasks.

Benchmark source: Ple Bench

Model	Score	Source
Claude Opus 5.5	70.3	Physical-Engineering's Last Exam: Claude Opus 5.5 on claude-code · Google
Claude Sonnet 5.5	57.9	Physical-Engineering's Last Exam: Claude Sonnet 5.5 on pi · Google
GPT-6 Astra	57.6	Physical-Engineering's Last Exam: GPT 6 Astra on codex · Google
Gemini 4 Argon	54.5	Physical-Engineering's Last Exam: Gemini 4 Argon on codex · Google
Claude Opus 5	52.5	Physical-Engineering's Last Exam: Claude Opus 5 on openhands · Google
Claude Fable 5	39.1	Physical-Engineering's Last Exam: Claude Fable 5 on claude-code · Google
Grok 4.7	37.1	Physical-Engineering's Last Exam: Grok 4.7 on grok-build · Google
Gemini 3.8 Flash	31.8	Physical-Engineering's Last Exam: Gemini 3.8 Flash on agy · Google
GLM-5.2	26.3	Physical-Engineering's Last Exam: GLM 5.2 on pi · Google
Gemini 3.1 Pro Preview	15.2	Physical-Engineering's Last Exam: Gemini 3.1 Pro on codex · Google
MiniMax M2	4.0	Physical-Engineering's Last Exam: MiniMax M2 on hermes · Google
Qwen3-Coder-480B-A35B-Instruct	3.6	Physical-Engineering's Last Exam: Qwen3 Coder 480B on agy · Google
Kimi K2 Thinking	3.4	Physical-Engineering's Last Exam: Kimi K2 Thinking on hermes · Google
Gemma 4 26B A4B IT	3.3	Physical-Engineering's Last Exam: Gemma 4 26B on pi · Google
gpt-oss-120b	3.3	Physical-Engineering's Last Exam: gpt-oss 120B on pi · Google
Qwen3 Next 80B A3B Instruct	2.1	Physical-Engineering's Last Exam: Qwen3-Next 80B on claude-code · Google
Llama 4 Maverick Instruct	0.2	Physical-Engineering's Last Exam: Llama 4 Maverick on openhands · Google