TuRTLe Code Completion (Icarus Verilog) Leaderboard — The Aggregate

TuRTLe Code Completion (Icarus Verilog) — leaderboard

TuRTLe leaderboard variant for RTL code completion evaluated with Icarus Verilog across VerilogEval MC and VeriGen.

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

Top models

#	Model	Score
1	GLM-5	83.98
2	Gemma 4 31B	82.57
3	DeepSeek R1 0528	78.86
4	GPT-OSS-120B	77.82
5	DeepSeek V3.1 Terminus	76.57
6	Qwen 3 235B A22B	67.54
7	GPT-OSS-20B	66.48
8	Llama 3.1 405B Instruct	54.74
9	Qwen 2.5 72B Instruct	50.41
10	Qwen 3 8B	48.16
11	Qwen 2.5 32B	41.4
12	QwQ-32B	40.05
13	starchat2-15B-v0.1	38.19
14	DeepSeek R1 Distill Qwen 14B	24.57
15	Magistral Small	22.62

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