rust-embedded/svd2rust | ProgramBench

Generate Rust register maps (`struct`s) from SVD files

918

Generated Behavioral Tests

99.1%

Best Score

Claude Opus 5.5 (xhigh)

Results by Model

Hover for details · Click a model to open it · Drag to zoom the x-axis · Shift-drag to pan · The line marks the Pareto frontier (best score per cost)

30 runs

#	Model	Score	Cost	Calls
1	Claude Opus 5.5 (xhigh)	99.1%	$75.00	504	trace →
2	Claude Fable 5.1 (xhigh)	98.0%	$114.63	467	trace →
3	Muse Wonder Full	97.6%	TBA	465	trace →
4	GPT 6 Astra (max)	96.9%	$20.12	97	trace →
5	Claude Opus 5 (xhigh)	93.2%	$93.27	429	trace →
6	Muse Wonder (xhigh)	89.9%	$47.33	465	trace →
7	Muse Spark 1.3 (xhigh)	83.6%	$2.84	308	trace →
8	GPT 5.5 (xhigh)	81.6%	$21.57	127	trace →
9	Muse Spark 1.3 (max)	77.1%	$14.84	471	trace →
10	GLM-5.2	75.3%	$53.01	291	trace →
11	Claude Sonnet 4.6	72.7%	$25.43	389	trace →
12	Muse Spark 1.2 (xhigh)	72.4%	$2.17	176	trace →
13	Claude Opus 4.8 (xhigh)	72.3%	$17.07	137	trace →
14	Gemini 3.6 Flash	69.4%	$3.84	121	trace →
15	GPT 5.5 (high)	68.6%	$4.94	39	trace →
16	Claude Opus 4.6	65.6%	$12.91	218	trace →
17	GPT 5.5	61.4%	$1.83	28	trace →
18	Claude Opus 4.7 (xhigh)	57.7%	$1.81	50	trace →
19	GPT-5.6 Sol	55.9%	$0.61	11	trace →
20	Gemini 3.1 Pro	45.3%	$1.86	117	trace →
21	Claude Haiku 4.5	30.5%	$0.66	92	trace →
22	GPT-5.6 Sol (xhigh)	15.9%	$13.54	75	trace →
23	Claude Opus 4.7	14.5%	$0.61	27	trace →
24	GPT 5.4	9.4%	$0.09	6	trace →
25	GPT 5.4 mini	8.0%	$0.03	9	trace →
26	GPT 5 mini	7.2%	$0.04	19	trace →
27	Gemini 3.7 Flash	4.4%	$1.12	94	trace →
28	Muse Spark 1.1 (xhigh)	0.8%	$0.41	141	trace →
29	Gemini 3 Flash	0.8%	$0.39	82	trace →
30	Gemini 3.5 Flash	0.0%	$11.97	149	trace →

Click a row to replay how that model rebuilt this program, or the model name to open its full run