Razavi-Bench -- Analog Design Reasoning Benchmark

Leaderboard

#	Model	Score	Range	Token	Cost

Score Distribution

Overall Active Score vs Resource Usage

Scored by DeepSeek V4 Pro across 50 tasks × 3 rollouts · Resource usage covers answer-model attempts only.

Token / Cost Composition

Evaluation Rubric

Score	Meaning	Criteria
4	Correct	Correct conclusion and reasoning; topology, device roles, dominant mechanism, trend, and key assumptions are right.
3	Mostly correct	Main conclusion is right, with a minor omission, imprecision, or modeling flaw that does not change the result.
2	Partially correct	Identifies some relevant mechanism, but misses an important circuit detail, trend, or design consequence.
1	Mostly incorrect	Main conclusion is wrong, but the answer contains a small amount of relevant circuit understanding.
0	Incorrect / unusable	Fundamentally wrong, internally inconsistent, or based on a mistaken topology/device/connection.

DeepSeek V4 Pro scores every answer against the golden solution, prioritizing analog-circuit reasoning over surface similarity. See GitHub for full details.

Citation

@misc{zhang2026razavibench,

  title        = {Razavi-Bench: An Expert-Curated Benchmark for Analog-Design Reasoning},

  author       = {Zhishuai Zhang},

  year         = {2026},

  howpublished = {\url{https://github.com/Arcadia-1/razavi-bench}},

  url          = {https://razavi-bench.tokenzhang.com/},

  note         = {Benchmark repository}

}