TuRTLe Spec-to-RTL (Icarus Verilog) Leaderboard — The Aggregate

TuRTLe Spec-to-RTL (Icarus Verilog) — leaderboard

TuRTLe leaderboard variant for spec-to-RTL generation evaluated with Icarus Verilog across VerilogEval S2R and RTLLM.

Metric: Aggregated Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 44 models tracked.

Top models

#	Model	Score
1	Gemma 4 31B	81.51
2	GLM-5	79.46
3	DeepSeek R1 0528	76.79
4	DeepSeek V3.1 Terminus	71.79
5	GPT-OSS-120B	70.52
6	Qwen 3 235B A22B	69.16
7	GPT-OSS-20B	63.7
8	QwQ-32B	62.6
9	Llama 3.1 405B Instruct	53.22
10	Qwen 2.5 32B	50.39
11	Qwen 2.5 72B Instruct	49.36
12	Qwen 3 8B	45.1
13	Magistral Small	40.82
14	starchat2-15B-v0.1	38.76
15	DeepSeek R1 Distill Qwen 14B	23.14

Interactive version: theaggregate.ai/benchmark?slug=turtle-spec-to-rtl-icarus-verilog · How the rankings work · Data refreshed daily, snapshot 2026-07-22.